Home | [11–20] << 21 22 23 24 25 26 27 28 29 30 >> [31–40] |
![]() |
Hassan Ahmed Sial. (2021). Estimating Light Effects from a Single Image: Deep Architectures and Ground-Truth Generation (Maria Vanrell, & Ramon Baldrich, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: In this thesis, we explore how to estimate the effects of the light interacting with the scene objects from a single image. To achieve this goal, we focus on recovering intrinsic components like reflectance, shading, or light properties such as color and position using deep architectures. The success of these approaches relies on training on large and diversified image datasets. Therefore, we present several contributions on this such as: (a) a data-augmentation technique; (b) a ground-truth for an existing multi-illuminant dataset; (c) a family of synthetic datasets, SID for Surreal Intrinsic Datasets, with diversified backgrounds and coherent light conditions; and (d) a practical pipeline to create hybrid ground-truths to overcome the complexity of acquiring realistic light conditions in a massive way. In parallel with the creation of datasets, we trained different flexible encoder-decoder deep architectures incorporating physical constraints from the image formation models.
In the last part of the thesis, we apply all the previous experience to two different problems. Firstly, we create a large hybrid Doc3DShade dataset with real shading and synthetic reflectance under complex illumination conditions, that is used to train a two-stage architecture that improves the character recognition task in complex lighting conditions of unwrapped documents. Secondly, we tackle the problem of single image scene relighting by extending both, the SID dataset to present stronger shading and shadows effects, and the deep architectures to use intrinsic components to estimate new relit images. |
Fei Yang. (2021). Towards Practical Neural Image Compression (Luis Herranz, Mikhail Mozerov, & Yongmei Cheng, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: Images and videos are pervasive in our life and communication. With advances in smart and portable devices, high capacity communication networks and high definition cinema, image and video compression are more relevant than ever. Traditional block-based linear transform codecs such as JPEG, H.264/AVC or the recent H.266/VVC are carefully designed to meet not only the rate-distortion criteria, but also the practical requirements of applications.
Recently, a new paradigm based on deep neural networks (i.e., neural image/video compression) has become increasingly popular due to its ability to learn powerful nonlinear transforms and other coding tools directly from data instead of being crafted by humans, as was usual in previous coding formats. While achieving excellent rate-distortion performance, these approaches are still limited mostly to research environments due to heavy models and other practical limitations, such as being limited to function on a particular rate and due to high memory and computational cost. In this thesis, we study these practical limitations, and designing more practical neural image compression approaches. After analyzing the differences between traditional and neural image compression, our first contribution is the modulated autoencoder (MAE), a framework that includes a mechanism to provide multiple rate-distortion options within a single model with comparable performance to independent models. In a second contribution, we propose the slimmable compressive autoencoder (SlimCAE), which in addition to variable rate, can optimize the complexity of the model and thus reduce significantly the memory and computational burden. Modern generative models can learn custom image transformation directly from suitable datasets following encoder-decoder architectures, task known as image-to-image (I2I) translation. Building on our previous work, we study the problem of distributed I2I translation, where the latent representation is transmitted through a binary channel and decoded in a remote receiving side. We also propose a variant that can perform both translation and the usual autoencoding functionality. Finally, we also consider neural video compression, where the autoencoder is typically augmented with temporal prediction via motion compensation. One of the main bottlenecks of that framework is the optical flow module that estimates the displacement to predict the next frame. Focusing on this module, we propose a method that improves the accuracy of the optical flow estimation and a simplified variant that reduces the computational cost. Key words: neural image compression, neural video compression, optical flow, practical neural image compression, compressive autoencoders, image-to-image translation, deep learning. |
Javad Zolfaghari Bengar. (2021). Reducing Label Effort with Deep Active Learning (Joost Van de Weijer, & Bogdan Raducanu, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: Deep convolutional neural networks (CNNs) have achieved superior performance in many visual recognition applications, such as image classification, detection and segmentation. Training deep CNNs requires huge amounts of labeled data, which is expensive and labor intensive to collect. Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected
informative and/or representative samples. In this thesis we study several aspects of active learning including video object detection for autonomous driving systems, image classification on balanced and imbalanced datasets and the incorporation of self-supervised learning in active learning. We briefly describe our approach in each of these areas to reduce the labeling effort. In chapter two we introduce a novel active learning approach for object detection in videos by exploiting temporal coherence. Our criterion is based on the estimated number of errors in terms of false positives and false negatives. Additionally, we introduce a synthetic video dataset, called SYNTHIA-AL, specially designed to evaluate active learning for video object detection in road scenes. Finally, we show that our approach outperforms active learning baselines tested on two outdoor datasets. In the next chapter we address the well-known problem of over confidence in the neural networks. As an alternative to network confidence, we propose a new informativeness-based active learning method that captures the learning dynamics of neural network with a metric called label-dispersion. This metric is low when the network consistently assigns the same label to the sample during the course of training and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results. In chapter four, we tackle the problem of sampling bias in active learning methods on imbalanced datasets. Active learning is generally studied on balanced datasets where an equal amount of images per class is available. However, real-world datasets suffer from severe imbalanced classes, the so called longtail distribution. We argue that this further complicates the active learning process, since the imbalanced data pool can result in suboptimal classifiers. To address this problem in the context of active learning, we propose a general optimization framework that explicitly takes class-balancing into account. Results on three datasets show that the method is general (it can be combined with most existing active learning algorithms) and can be effectively applied to boost the performance of both informative and representative-based active learning methods. In addition, we show that also on balanced datasets our method generally results in a performance gain. Another paradigm to reduce the annotation effort is self-training that learns from a large amount of unlabeled data in an unsupervised way and fine-tunes on few labeled samples. Recent advancements in self-training have achieved very impressive results rivaling supervised learning on some datasets. In the last chapter we focus on whether active learning and self supervised learning can benefit from each other. We study object recognition datasets with several labeling budgets for the evaluations. Our experiments reveal that self-training is remarkably more efficient than active learning at reducing the labeling effort, that for a low labeling budget, active learning offers no benefit to self-training, and finally that the combination of active learning and self-training is fruitful when the labeling budget is high. |
Vacit Oguz Yazici. (2022). Towards Smart Fashion: Visual Recognition of Products and Attributes (Joost Van de Weijer, & Arnau Ramisa, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: Artificial intelligence is innovating the fashion industry by proposing new applications and solutions to the problems encountered by researchers and engineers working in the industry. In this thesis, we address three of these problems. In the first part of the thesis, we tackle the problem of multi-label image classification which is very related to fashion attribute recognition. In the second part of the thesis, we address two problems that are specific to fashion. Firstly, we address the problem of main product detection which is the task of associating correct image parts (e.g. bounding boxes) with the fashion product being sold. Secondly, we address the problem of color naming for multicolored fashion items. The task of multi-label image classification consists in assigning various concepts such as objects or attributes to images. Usually, there are dependencies that can be learned between the concepts to capture label correlations (chair and table classes are more likely to co-exist than chair and giraffe).
If we treat the multi-label image classification problem as an orderless set prediction problem, we can exploit recurrent neural networks (RNN) to capture label correlations. However, RNNs are trained to predict ordered sequences of tokens, so if the order of the predicted sequence is different than the order of the ground truth sequence, there will be penalization although the predictions are correct. Therefore, in the first part of the thesis, we propose an orderless loss function which will order the labels in the ground truth sequence dynamically in a way that the minimum loss is achieved. This results in a significant improvement of RNN models on multi-label image classification over the previous methods. However, RNNs suffer from long term dependencies when the cardinality of set grows bigger. The decoding process might stop early if the current hidden state cannot find any object and outputs the termination token. This would cause the remaining classes not to be predicted and lower recall metric. Transformers can be used to avoid the long term dependency problem exploiting their selfattention modules that process sequential data simultaneously. Consequently, we propose a novel transformer model for multi-label image classification which surpasses the state-of-the-art results by a large margin. In the second part of thesis, we focus on two fashion-specific problems. Main product detection is the task of associating image parts with the fashion product that is being sold, generally using associated textual metadata (product title or description). Normally, in fashion e-commerces, products are represented by multiple images where a person wears the product along with other fashion items. If all the fashion items in the images are marked with bounding boxes, we can use the textual metadata to decide which item is the main product. The initial work treated each of these images independently, discarding the fact that they all belong to the same product. In this thesis, we represent the bounding boxes from all the images as nodes in a fully connected graph. This allows the algorithm to learn relations between the nodes during training and take the entire context into account for the final decision. Our algorithm results in a significant improvement of the state-ofthe-art. Moreover, we address the problem of color naming for multicolored fashion items, which is a challenging task due to the external factors such as illumination changes or objects that act as clutter. In the context of multi-label classification, the vaguely defined lines between the classes in the color space cause ambiguity. For example, a shade of blue which is very close to green might cause the model to incorrectly predict the color blue and green at the same time. Based on this, models trained for color naming are expected to recognize the colors and their quantities in both single colored and multicolored fashion items. Therefore, in this thesis, we propose a novel architecture with an additional head that explicitly estimates the number of colors in fashion items. This removes the ambiguity problem and results in better color naming performance. |
Akhil Gurram. (2022). Monocular Depth Estimation for Autonomous Driving (Antonio Lopez, & Onay Urfalioglu, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: 3D geometric information is essential for on-board perception in autonomous driving and driver assistance. Autonomous vehicles (AVs) are equipped with calibrated sensor suites. As part of these suites, we can find LiDARs, which are expensive active sensors in charge of providing the 3D geometric information. Depending on the operational conditions for the AV, calibrated stereo rigs may be also sufficient for obtaining 3D geometric information, being these rigs less expensive and easier to install than LiDARs. However, ensuring a proper maintenance and calibration of these types of sensors is not trivial. Accordingly, there is an increasing interest on performing monocular depth estimation (MDE) to obtain 3D geometric information on-board. MDE is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Moreover, a set of single cameras with MDE capabilities would still be a cheap solution for on-board perception, relatively easy to integrate and maintain in an AV.
Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Accordingly, the overall goal of this PhD is to study methods for improving CNN-based MDE accuracy under different training settings. More specifically, this PhD addresses different research questions that are described below. When we started to work in this PhD, state-of-theart methods for MDE were already based on CNNs. In fact, a promising line of work consisted in using image-based semantic supervision (i.e., pixel-level class labels) while training CNNs for MDE using LiDAR-based supervision (i.e., depth). It was common practice to assume that the same raw training data are complemented by both types of supervision, i.e., with depth and semantic labels. However, in practice, it was more common to find heterogeneous datasets with either only depth supervision or only semantic supervision. Therefore, our first work was to research if we could train CNNs for MDE by leveraging depth and semantic information from heterogeneous datasets. We show that this is indeed possible, and we surpassed the state-of-the-art results on MDE at the time we did this research. To achieve our results, we proposed a particular CNN architecture and a new training protocol. After this research, it was clear that the upper-bound setting to train CNN-based MDE models consists in using LiDAR data as supervision. However, it would be cheaper and more scalable if we would be able to train such models from monocular sequences. Obviously, this is far more challenging, but worth to research. Training MDE models using monocular sequences is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. To alleviate these problems, we perform MDE by virtual-world supervision and real-world SfM self-supervision. We call our proposalMonoDEVSNet. We compensate the SfM self-supervision limitations by leveraging virtual-world images with accurate semantic and depth supervision, as well as addressing the virtual-to-real domain gap. MonoDEVSNet outperformed previous MDE CNNs trained on monocular and even stereo sequences. We have publicly released MonoDEVSNet at <https://github.com/HMRC-AEL/MonoDEVSNet>. Finally, since MDE is performed to produce 3D information for being used in downstream tasks related to on-board perception. We also address the question of whether the standard metrics for MDE assessment are a good indicator for future MDE-based driving-related perception tasks. By using 3D object detection on point clouds as proxy of on-board perception, we conclude that, indeed, MDE evaluation metrics give rise to a ranking of methods which reflects relatively well the 3D object detection results we may expect. |
Arnau Baro. (2022). Reading Music Systems: From Deep Optical Music Recognition to Contextual Methods (Alicia Fornes, Ed.). Ph.D. thesis, IMPRIMA, .
Abstract: The transcription of sheet music into some machine-readable format can be carried out manually. However, the complexity of music notation inevitably leads to burdensome software for music score editing, which makes the whole process
very time-consuming and prone to errors. Consequently, automatic transcription systems for musical documents represent interesting tools. Document analysis is the subject that deals with the extraction and processing of documents through image and pattern recognition. It is a branch of computer vision. Taking music scores as source, the field devoted to address this task is known as Optical Music Recognition (OMR). Typically, an OMR system takes an image of a music score and automatically extracts its content into some symbolic structure such as MEI or MusicXML. In this dissertation, we have investigated different methods for recognizing a single staff section (e.g. scores for violin, flute, etc.), much in the same way as most text recognition research focuses on recognizing words appearing in a given line image. These methods are based in two different methodologies. On the one hand, we present two methods based on Recurrent Neural Networks, in particular, the Long Short-Term Memory Neural Network. On the other hand, a method based on Sequence to Sequence models is detailed. Music context is needed to improve the OMR results, just like language models and dictionaries help in handwriting recognition. For example, syntactical rules and grammars could be easily defined to cope with the ambiguities in the rhythm. In music theory, for example, the time signature defines the amount of beats per bar unit. Thus, in the second part of this dissertation, different methodologies have been investigated to improve the OMR recognition. We have explored three different methods: (a) a graphic tree-structure representation, Dendrograms, that joins, at each level, its primitives following a set of rules, (b) the incorporation of Language Models to model the probability of a sequence of tokens, and (c) graph neural networks to analyze the music scores to avoid meaningless relationships between music primitives. Finally, to train all these methodologies, and given the method-specificity of the datasets in the literature, we have created four different music datasets. Two of them are synthetic with a modern or old handwritten appearance, whereas the other two are real handwritten scores, being one of them modern and the other old. |
Ali Furkan Biten. (2022). A Bitter-Sweet Symphony on Vision and Language: Bias and World Knowledge (Dimosthenis Karatzas, & Lluis Gomez, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: Vision and Language are broadly regarded as cornerstones of intelligence. Even though language and vision have different aims – language having the purpose of communication, transmission of information and vision having the purpose of constructing mental representations around us to navigate and interact with objects – they cooperate and depend on one another in many tasks we perform effortlessly. This reliance is actively being studied in various Computer Vision tasks, e.g. image captioning, visual question answering, image-sentence retrieval, phrase grounding, just to name a few. All of these tasks share the inherent difficulty of the aligning the two modalities, while being robust to language
priors and various biases existing in the datasets. One of the ultimate goal for vision and language research is to be able to inject world knowledge while getting rid of the biases that come with the datasets. In this thesis, we mainly focus on two vision and language tasks, namely Image Captioning and Scene-Text Visual Question Answering (STVQA). In both domains, we start by defining a new task that requires the utilization of world knowledge and in both tasks, we find that the models commonly employed are prone to biases that exist in the data. Concretely, we introduce new tasks and discover several problems that impede performance at each level and provide remedies or possible solutions in each chapter: i) We define a new task to move beyond Image Captioning to Image Interpretation that can utilize Named Entities in the form of world knowledge. ii) We study the object hallucination problem in classic Image Captioning systems and develop an architecture-agnostic solution. iii) We define a sub-task of Visual Question Answering that requires reading the text in the image (STVQA), where we highlight the limitations of current models. iv) We propose an architecture for the STVQA task that can point to the answer in the image and show how to combine it with classic VQA models. v) We show how far language can get us in STVQA and discover yet another bias which causes the models to disregard the image while doing Visual Question Answering. |
Andres Mafla. (2022). Leveraging Scene Text Information for Image Interpretation (Dimosthenis Karatzas, & Lluis Gomez, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: Until recently, most computer vision models remained illiterate, largely ignoring the semantically rich and explicit information contained in scene text. Recent progress in scene text detection and recognition has recently allowed exploring its role in a diverse set of open computer vision problems, e.g. image classification, image-text retrieval, image captioning, and visual question answering to name a few. The explicit semantics of scene text closely requires specific modeling similar to language. However, scene text is a particular signal that has to be interpreted according to a comprehensive perspective that encapsulates all the visual cues in an image. Incorporating this information is a straightforward task for humans, but if we are unfamiliar with a language or scripture, achieving a complete world understanding is impossible (e.a. visiting a foreign country with a different alphabet). Despite the importance of scene text, modeling it requires considering the several ways in which scene text interacts with an image, processing and fusing an additional modality. In this thesis, we mainly focus
on two tasks, scene text-based fine-grained image classification, and cross-modal retrieval. In both studied tasks we identify existing limitations in current approaches and propose plausible solutions. Concretely, in each chapter: i) We define a compact way to embed scene text that generalizes to unseen words at training time while performing in real-time. ii) We incorporate the previously learned scene text embedding to create an image-level descriptor that overcomes optical character recognition (OCR) errors which is well-suited to the fine-grained image classification task. iii) We design a region-level reasoning network that learns the interaction through semantics among salient visual regions and scene text instances. iv) We employ scene text information in image-text matching and introduce the Scene Text Aware Cross-Modal retrieval StacMR task. We gather a dataset that incorporates scene text and design a model suited for the newly studied modality. v) We identify the drawbacks of current retrieval metrics in cross-modal retrieval. An image captioning metric is proposed as a way of better evaluating semantics in retrieved results. Ample experimentation shows that incorporating such semantics into a model yields better semantic results while requiring significantly less data to converge. |
Mohamed Ali Souibgui. (2022). Document Image Enhancement and Recognition in Low Resource Scenarios: Application to Ciphers and Handwritten Text (Alicia Fornes, & Yousri Kessentini, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: In this thesis, we propose different contributions with the goal of enhancing and recognizing historical handwritten document images, especially the ones with rare scripts, such as cipher documents.
In the first part, some effective end-to-end models for Document Image Enhancement (DIE) using deep learning models were presented. First, Generative Adversarial Networks (cGAN) for different tasks (document clean-up, binarization, deblurring, and watermark removal) were explored. Next, we further improve the results by recovering the degraded document images into a clean and readable form by integrating a text recognizer into the cGAN model to promote the generated document image to be more readable. Afterward, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion. The second part of the thesis addresses Handwritten Text Recognition (HTR) in low resource scenarios, i.e. when only few labeled training data is available. We propose novel methods for recognizing ciphers with rare scripts. First, a few-shot object detection based method was proposed. Then, we incorporate a progressive learning strategy that automatically assignspseudo-labels to a set of unlabeled data to reduce the human labor of annotating few pages while maintaining the good performance of the model. Secondly, a data generation technique based on Bayesian Program Learning (BPL) is proposed to overcome the lack of data in such rare scripts. Thirdly, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE). This latter self-supervised model is designed to tackle two tasks, text recognition and document image enhancement. The proposed model does not exhibit limitations of previous state-of-the-art methods based on contrastive losses, while at the same time, it requires substantially fewer data samples to converge. In the third part of the thesis, we analyze, from the user perspective, the usage of HTR systems in low resource scenarios. This contrasts with the usual research on HTR, which often focuses on technical aspects only and rarely devotes efforts on implementing software tools for scholars in Humanities. |
Armin Mehri. (2023). Deep learning based architectures for cross-domain image processing (Angel Sappa, Ed.). Ph.D. thesis, IMPRIMA, .
Abstract: Human vision is restricted to the visual-optical spectrum. Machine vision is not.
Cameras sensitive to diverse infrared spectral bands can improve the capacities of autonomous systems and provide a comprehensive view. Relevant scene content can be made visible, particularly in situations when sensors of other modalities, such as a visual-optical camera, require a source of illumination. As a result, increasing the level of automation not only avoids human errors but also reduces machine-induced errors. Furthermore, multi-spectral sensor systems with infrared imagery as one modality are a rich source of information and can conceivably increase the robustness of many autonomous systems. Robotics, automobiles, biometrics, security, surveillance, and the military are some examples of fields that can profit from the use of infrared imagery in their respective applications. Although multimodal spectral sensors have come a long way, there are still several bottlenecks that prevent us from combining their output information and using them as comprehensive images. The primary issue with infrared imaging is the lack of potential benefits due to their cost influence on sensor resolution, which grows exponentially with greater resolution. Due to the more costly sensor technology required for their development, their resolutions are substantially lower than thoseof regular digital cameras. This thesis aims to improve beyond-visible-spectrum machine vision by integrating multi-modal spectral sensors. The emphasis is on transforming the produced images to enhance their resolution to match expected human perception, bring the color representation close to human understanding of natural color, and improve machine vision application performance. This research focuses mainly on two tasks, image Colorization and Image Super resolution for both single- and cross-domain problems. We first start with an extensive review of the state of the art in both tasks, point out the shortcomings of existing approaches, and then present our solutions to address their limitations. Our solutions demonstrate that low-cost channel information (i.e., visible image) can be used to improve expensive channel information (i.e., infrared image), resulting in images with higher quality and closer to human perception at a lower cost than a high-cost infrared camera. |
Chenshen Wu. (2023). Going beyond Classification Problems for the Continual Learning of Deep Neural Networks (Joost Van de Weijer, & Bogdan Raducanu, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: Deep learning has made tremendous progress in the last decade due to the explosion of training data and computational power. Through end-to-end training on a
large dataset, image representations are more discriminative than the previously used hand-crafted features. However, for many real-world applications, training and testing on a single dataset is not realistic, as the test distribution may change over time. Continuous learning takes this situation into account, where the learner must adapt to a sequence of tasks, each with a different distribution. If you would naively continue training the model with a new task, the performance of the model would drop dramatically for the previously learned data. This phenomenon is known as catastrophic forgetting. Many approaches have been proposed to address this problem, which can be divided into three main categories: regularization-based approaches, rehearsal-based approaches, and parameter isolation-based approaches. However, most of the existing works focus on image classification tasks and many other computer vision tasks have not been well-explored in the continual learning setting. Therefore, in this thesis, we study continual learning for image generation, object re-identification, and object counting. For the image generation problem, since the model can generate images from the previously learned task, it is free to apply rehearsal without any limitation. We developed two methods based on generative replay. The first one uses the generated image for joint training together with the new data. The second one is based on output pixel-wise alignment. We extensively evaluate these methods on several benchmarks. Next, we study continual learning for object Re-Identification (ReID). Although most state-of-the-art methods of ReID and continual ReID use softmax-triplet loss, we found that it is better to solve the ReID problem from a meta-learning perspective because continual learning of reID can benefit a lot from the generalization of metalearning. We also propose a distillation loss and found that the removal of the positive pairs before the distillation loss is critical. Finally, we study continual learning for the counting problem. We study the mainstream method based on density maps and propose a new approach for density map distillation. We found that fixing the counter head is crucial for the continual learning of object counting. To further improve results, we propose an adaptor to adapt the changing feature extractor for the fixed counter head. Extensive evaluation shows that this results in improved continual learning performance. |
Jose Luis Gomez. (2023). Synth-to-real semi-supervised learning for visual tasks (Antonio Lopez, Ed.). Ph.D. thesis, IMPRIMA, .
Abstract: The curse of data labeling is a costly bottleneck in supervised deep learning, where large amounts of labeled data are needed to train intelligent systems. In onboard perception for autonomous driving, this cost corresponds to the labeling of raw data from sensors such as cameras, LiDARs, RADARs, etc. Therefore, synthetic data with automatically generated ground truth (labels) has aroused as a reliable alternative for training onboard perception models.
However, synthetic data commonly suffers from synth-to-real domain shift, i.e., models trained on the synthetic domain do not show their achievable accuracy when performing in the real world. This shift needs to be addressed by techniques falling in the realm of domain adaptation (DA). The semi-supervised learning (SSL) paradigm can be followed to address DA. In this case, a model is trained using source data with labels (here synthetic) and leverages minimal knowledge from target data (here the real world) to generate pseudo-labels. These pseudo-labels help the training process to reduce the gap between the source and the target domains. In general, we can assume accessing both, pseudo-labels and a few amounts of human-provided labels for the target-domain data. However, the most interesting and challenging setting consists in assuming that we do not have human-provided labels at all. This setting is known as unsupervised domain adaptation (UDA). This PhD focuses on applying SSL to the UDA setting, for onboard visual tasks related to autonomous driving. We start by addressing the synth-to-real UDA problem on onboard vision-based object detection (pedestrians and cars), a critical task for autonomous driving and driving assistance. In particular, we propose to apply an SSL technique known as co-training, which we adapt to work with deep models that process a multi-modal input. The multi-modality consists of the visual appearance of the images (RGB) and their monocular depth estimation. The synthetic data we use as the source domain contains both, object bounding boxes and depth information. This prior knowledge is the starting point for the co-training technique, which iteratively labels unlabeled real-world data and uses such pseudolabels (here bounding boxes with an assigned object class) to progressively improve the labeling results. Along this process, two models collaborate to automatically label the images, in a way that one model compensates for the errors of the other, so avoiding error drift. While this automatic labeling process is done offline, the resulting pseudolabels can be used to train object detection models that must perform in real-time onboard a vehicle. We show that multi-modal co-training improves the labeling results compared to single-modal co-training, remaining competitive compared to human labeling. Given the success of co-training in the context of object detection, we have also adapted this technique to a more crucial and challenging visual task, namely, onboard semantic segmentation. In fact, providing labels for a single image can take from 30 to 90 minutes for a human labeler, depending on the content of the image. Thus, developing automatic labeling techniques for this visual task is of great interest to the automotive industry. In particular, the new co-training framework addresses synth-to-real UDA by an initial stage of self-training. Intermediate models arising from this stage are used to start the co-training procedure, for which we have elaborated an accurate collaboration policy between the two models performing the automatic labeling. Moreover, our co-training seamlessly leverages datasets from different synthetic domains. In addition, the co-training procedure is agnostic to the loss function used to train the semantic segmentation models which perform the automatic labeling. We achieve state-of-the-art results on publicly available benchmark datasets, again, remaining competitive compared to human labeling. Finally, on the ground of our previous experience, we have designed and implemented a new SSL technique for UDA in the context of visual semantic segmentation. In this case, we mimic the labeling methodology followed by human labelers. In particular, rather than labeling full images at a time, categories of semantic classes are defined and only those are labeled in a labeling pass. In fact, different human labelers can become specialists in labeling different categories. Afterward, these per-category-labeled layers are combined to provide fully labeled images. Our technique is inspired by this methodology since we perform synth-to-real UDA per category, using the self-training stage previously developed as part of our co-training framework. The pseudo-labels obtained for each category are finally fused to obtain fully automatically labeled images. In this context, we have also contributed to the development of a new photo-realistic synthetic dataset based on path-tracing rendering. Our new SSL technique seamlessly leverages publicly available synthetic datasets as well as this new one to obtain state-of-the-art results on synth-to-real UDA for semantic segmentation. We show that the new dataset allows us to reach better labeling accuracy than previously existing datasets, at the same time that it complements well them when combined. Moreover, we also show that the new human-inspired SSL technique outperforms co-training. |
Jose Elias Yauri. (2023). Deep Learning Based Data Fusion Approaches for the Assessment of Cognitive States on EEG Signals (Aura Hernandez, & Debora Gil, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: For millennia, the study of the couple brain-mind has fascinated the humanity in order to understand the complex nature of cognitive states. A cognitive state is the state of the mind at a specific time and involves cognition activities to acquire and process information for making a decision, solving a problem, or achieving a goal.
While normal cognitive states assist in the successful accomplishment of tasks; on the contrary, abnormal states of the mind can lead to task failures due to a reduced cognition capability. In this thesis, we focus on the assessment of cognitive states by means of the analysis of ElectroEncephaloGrams (EEG) signals using deep learning methods. EEG records the electrical activity of the brain using a set of electrodes placed on the scalp that output a set of spatiotemporal signals that are expected to be correlated to a specific mental process. From the point of view of artificial intelligence, any method for the assessment of cognitive states using EEG signals as input should face several challenges. On the one hand, one should determine which is the most suitable approach for the optimal combination of the multiple signals recorded by EEG electrodes. On the other hand, one should have a protocol for the collection of good quality unambiguous annotated data, and an experimental design for the assessment of the generalization and transfer of models. In order to tackle them, first, we propose several convolutional neural architectures to perform data fusion of the signals recorded by EEG electrodes, at raw signal and feature levels. Four channel fusion methods, easy to incorporate into any neural network architecture, are proposed and assessed. Second, we present a method to create an unambiguous dataset for the prediction of cognitive mental workload using serious games and an Airbus-320 flight simulator. Third, we present a validation protocol that takes into account the levels of generalization of models based on the source and amount of test data. Finally, the approaches for the assessment of cognitive states are applied to two use cases of high social impact: the assessment of mental workload for personalized support systems in the cockpit and the detection of epileptic seizures. The results obtained from the first use case show the feasibility of task transfer of models trained to detect workload in serious games to real flight scenarios. The results from the second use case show the generalization capability of our EEG channel fusion methods at k-fold cross-validation, patient-specific, and population levels. |
Shiqi Yang. (2023). Towards Source-Free Domain Adaption of Neural Networks in an Open World (Joost, Ed.). Ph.D. thesis, IMPRIMA, .
Abstract: Though they achieve great success, deep neural networks typically require a huge
amount of labeled data for training. However, collecting labeled data is often laborious and expensive. It would, therefore, be ideal if the knowledge obtained from label-rich datasets could be transferred to unlabeled data. However, deep networks are weak at generalizing to unseen domains, even when the differences are only subtle between the datasets. In real-world situations, a typical factor impairing the model generalization ability is the distribution shift between data from different domains, which is a long-standing problem usually termed as (unsupervised) domain adaptation. A crucial requirement in the methodology of these domain adaptation methods is that they require access to source domain data during the adaptation process to the target domain. Accessibility to the source data of a trained source model is often impossible in real-world applications, for example, when deploying domain adaptation algorithms on mobile devices where the computational capacity is limited or in situations where data privacy rules limit access to the source domain data. Without access to the source domain data, existing methods suffer from inferior performance. Thus, in this thesis, we investigate domain adaptation without source data (termed as source-free domain adaptation) in multiple different scenarios that focus on image classification tasks. We first study the source-free domain adaptation problem in a closed-set setting, where the label space of different domains is identical. Only accessing the pretrained source model, we propose to address source-free domain adaptation from the perspective of unsupervised clustering. We achieve this based on nearest neighborhood clustering. In this way, we can transfer the challenging source-free domain adaptation task to a type of clustering problem. The final optimization objective is an upper bound containing only two simple terms, which can be explained as discriminability and diversity. We show that this allows us to relate several other methods in domain adaptation, unsupervised clustering and contrastive learning via the perspective of discriminability and diversity. |
Yi Xiao. (2023). Advancing Vision-based End-to-End Autonomous Driving (Antonio Lopez, Ed.). Ph.D. thesis, IMPRIMA, .
Abstract: In autonomous driving, artificial intelligence (AI) processes the traffic environment to drive the vehicle to a desired destination. Currently, there are different paradigms that address the development of AI-enabled drivers. On the one hand, we find modular pipelines, which divide the driving task into sub-tasks such as perception, maneuver planning, and control. On the other hand, we find end-to-end driving approaches that attempt to learn the direct mapping of raw data from input sensors to vehicle control signals. The latter are relatively less studied but are gaining popularity as they are less demanding in terms of data labeling. Therefore, in this thesis, our goal is to investigate end-to-end autonomous driving.
We propose to evaluate three approaches to tackle the challenge of end-to-end autonomous driving. First, we focus on the input, considering adding depth information as complementary to RGB data, in order to mimic the human being’s ability to estimate the distance to obstacles. Notice that, in the real world, these depth maps can be obtained either from a LiDAR sensor, or a trained monocular depth estimation module, where human labeling is not needed. Then, based on the intuition that the latent space of end-to-end driving models encodes relevant information for driving, we use it as prior knowledge for training an affordancebased driving model. In this case, the trained affordance-based model can achieve good performance while requiring less human-labeled data, and it can provide interpretability regarding driving actions. Finally, we present a new pure vision-based end-to-end driving model termed CIL++, which is trained by imitation learning. CIL++ leverages modern best practices, such as a large horizontal field of view and a self-attention mechanism, which are contributing to the agent’s understanding of the driving scene and bringing a better imitation of human drivers. Using training data without any human labeling, our model yields almost expert performance in the CARLA NoCrash benchmark and could rival SOTA models that require large amounts of human-labeled data. |