|
Idoia Ruiz. 2022. Deep Metric Learning for re-identification, tracking and hierarchical novelty detection. (Ph.D. thesis, .)
Abstract: Metric learning refers to the problem in machine learning of learning a distance or similarity measurement to compare data. In particular, deep metric learning involves learning a representation, also referred to as embedding, such that in the embedding space data samples can be compared based on the distance, directly providing a similarity measure. This step is necessary to perform several tasks in computer vision. It allows to perform the classification of images, regions or pixels, re-identification, out-of-distribution detection, object tracking in image sequences and any other task that requires computing a similarity score for their solution. This thesis addresses three specific problems that share this common requirement. The first one is person re-identification. Essentially, it is an image retrieval task that aims at finding instances of the same person according to a similarity measure. We first compare in terms of accuracy and efficiency, classical metric learning to basic deep learning based methods for this problem. In this context, we also study network distillation as a strategy to optimize the trade-off between accuracy and speed at inference time. The second problem we contribute to is novelty detection in image classification. It consists in detecting samples of novel classes, i.e. never seen during training. However, standard novelty detection does not provide any information about the novel samples besides they are unknown. Aiming at more informative outputs, we take advantage from the hierarchical taxonomies that are intrinsic to the classes. We propose a metric learning based approach that leverages the hierarchical relationships among classes during training, being able to predict the parent class for a novel sample in such hierarchical taxonomy. Our third contribution is in multi-object tracking and segmentation. This joint task comprises classification, detection, instance segmentation and tracking. Tracking can be formulated as a retrieval problem to be addressed with metric learning approaches. We tackle the existing difficulty in academic research that is the lack of annotated benchmarks for this task. To this matter, we introduce the problem of weakly supervised multi-object tracking and segmentation, facing the challenge of not having available ground truth for instance segmentation. We propose a synergistic training strategy that benefits from the knowledge of the supervised tasks that are being learnt simultaneously.
|
|
|
Jose Luis Gomez. 2023. Synth-to-real semi-supervised learning for visual tasks. (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.
|
|
|
Yi Xiao. 2023. Advancing Vision-based End-to-End Autonomous Driving. (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.
|
|
|
David Geronimo, David Vazquez and Arturo de la Escalera. 2017. Vision-Based Advanced Driver Assistance Systems. Computer Vision in Vehicle Technology: Land, Sea, and Air.
Keywords: ADAS; Autonomous Driving
|
|
|
David Geronimo and Antonio Lopez. 2014. Vision-based Pedestrian Protection Systems for Intelligent Vehicles. Springer Briefs in Computer Vision.
Abstract: Pedestrian Protection Systems (PPSs) are on-board systems aimed at detecting and tracking people in the surroundings of a vehicle in order to avoid potentially dangerous situations. These systems, together with other Advanced Driver Assistance Systems (ADAS) such as lane departure warning or adaptive cruise control, are one of the most promising ways to improve traffic safety. By the use of computer vision, cameras working either in the visible or infra-red spectra have been demonstrated as a reliable sensor to perform this task. Nevertheless, the variability of human’s appearance, not only in terms of clothing and sizes but also as a result of their dynamic shape, makes pedestrians one of the most complex classes even for computer vision. Moreover, the unstructured changing and unpredictable environment in which such on-board systems must work makes detection a difficult task to be carried out with the demanded robustness. In this brief, the state of the art in PPSs is introduced through the review of the most relevant papers of the last decade. A common computational architecture is presented as a framework to organize each method according to its main contribution. More than 300 papers are referenced, most of them addressing pedestrian detection and others corresponding to the descriptors (features), pedestrian models, and learning machines used. In addition, an overview of topics such as real-time aspects, systems benchmarking and future challenges of this research area are presented.
Keywords: Computer Vision; Driver Assistance Systems; Intelligent Vehicles; Pedestrian Detection; Vulnerable Road Users
|
|
|
Jose M. Armingol and 11 others. 2018. Environmental Perception for Intelligent Vehicles. Intelligent Vehicles. Enabling Technologies and Future Developments.23–101.
Abstract: Environmental perception represents, because of its complexity, a challenge for Intelligent Transport Systems due to the great variety of situations and different elements that can happen in road environments and that must be faced by these systems. In connection with this, so far there are a variety of solutions as regards sensors and methods, so the results of precision, complexity, cost, or computational load obtained by these works are different. In this chapter some systems based on computer vision and laser techniques are presented. Fusion methods are also introduced in order to provide advanced and reliable perception systems.
Keywords: Computer vision; laser techniques; data fusion; advanced driver assistance systems; traffic monitoring systems; intelligent vehicles
|
|
|
Antonio Lopez, Jiaolong Xu, Jose Luis Gomez, David Vazquez and German Ros. 2017. From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example. In Gabriela Csurka, ed. Domain Adaptation in Computer Vision Applications. Springer, 243–258.
Abstract: Supervised learning tends to produce more accurate classifiers than unsupervised learning in general. This implies that training data is preferred with annotations. When addressing visual perception challenges, such as localizing certain object classes within an image, the learning of the involved classifiers turns out to be a practical bottleneck. The reason is that, at least, we have to frame object examples with bounding boxes in thousands of images. A priori, the more complex the model is regarding its number of parameters, the more annotated examples are required. This annotation task is performed by human oracles, which ends up in inaccuracies and errors in the annotations (aka ground truth) since the task is inherently very cumbersome and sometimes ambiguous. As an alternative we have pioneered the use of virtual worlds for collecting such annotations automatically and with high precision. However, since the models learned with virtual data must operate in the real world, we still need to perform domain adaptation (DA). In this chapter we revisit the DA of a deformable part-based model (DPM) as an exemplifying case of virtual- to-real-world DA. As a use case, we address the challenge of vehicle detection for driver assistance, using different publicly available virtual-world data. While doing so, we investigate questions such as: how does the domain gap behave due to virtual-vs-real data with respect to dominant object appearance per domain, as well as the role of photo-realism in the virtual world.
Keywords: Domain Adaptation
|
|
|
Antonio Lopez, David Vazquez and Gabriel Villalonga. 2018. Data for Training Models, Domain Adaptation. Intelligent Vehicles. Enabling Technologies and Future Developments.395–436.
Abstract: Simulation can enable several developments in the field of intelligent vehicles. This chapter is divided into three main subsections. The first one deals with driving simulators. The continuous improvement of hardware performance is a well-known fact that is allowing the development of more complex driving simulators. The immersion in the simulation scene is increased by high fidelity feedback to the driver. In the second subsection, traffic simulation is explained as well as how it can be used for intelligent transport systems. Finally, it is rather clear that sensor-based perception and action must be based on data-driven algorithms. Simulation could provide data to train and test algorithms that are afterwards implemented in vehicles. These tools are explained in the third subsection.
Keywords: Driving simulator; hardware; software; interface; traffic simulation; macroscopic simulation; microscopic simulation; virtual data; training data
|
|
|
Lluis Pere de las Heras, Ernest Valveny and Gemma Sanchez. 2014. Unsupervised and Notation-Independent Wall Segmentation in Floor Plans Using a Combination of Statistical and Structural Strategies. Graphics Recognition. Current Trends and Challenges. Springer Berlin Heidelberg, 109–121. (LNCS.)
Abstract: In this paper we present a wall segmentation approach in floor plans that is able to work independently to the graphical notation, does not need any pre-annotated data for learning, and is able to segment multiple-shaped walls such as beams and curved-walls. This method results from the combination of the wall segmentation approaches [3, 5] presented recently by the authors. Firstly, potential straight wall segments are extracted in an unsupervised way similar to [3], but restricting even more the wall candidates considered in the original approach. Then, based on [5], these segments are used to learn the texture pattern of walls and spot the lost instances. The presented combination of both methods has been tested on 4 available datasets with different notations and compared qualitatively and quantitatively to the state-of-the-art applied on these collections. Additionally, some qualitative results on floor plans directly downloaded from the Internet are reported in the paper. The overall performance of the method demonstrates either its adaptability to different wall notations and shapes, and to document qualities and resolutions.
Keywords: Graphics recognition; Floor plan analysis; Object segmentation
|
|
|
Lluis Pere de las Heras, David Fernandez, Alicia Fornes, Ernest Valveny, Gemma Sanchez and Josep Llados. 2014. Runlength Histogram Image Signature for Perceptual Retrieval of Architectural Floor Plans. Graphics Recognition. Current Trends and Challenges. Springer Berlin Heidelberg, 135–146. (LNCS.)
Abstract: This paper proposes a runlength histogram signature as a perceptual descriptor of architectural plans in a retrieval scenario. The style of an architectural drawing is characterized by the perception of lines, shapes and texture. Such visual stimuli are the basis for defining semantic concepts as space properties, symmetry, density, etc. We propose runlength histograms extracted in vertical, horizontal and diagonal directions as a characterization of line and space properties in floorplans, so it can be roughly associated to a description of walls and room structure. A retrieval application illustrates the performance of the proposed approach, where given a plan as a query, similar ones are obtained from a database. A ground truth based on human observation has been constructed to validate the hypothesis. Additional retrieval results on sketched building’s facades are reported qualitatively in this paper. Its good description and its adaptability to two different sketch drawings despite its simplicity shows the interest of the proposed approach and opens a challenging research line in graphics recognition.
Keywords: Graphics recognition; Graphics retrieval; Image classification
|
|