|
|
Eloi Puertas, Sergio Escalera, & Oriol Pujol. (2010). Classifying Objects at Different Sizes with Multi-Scale Stacked Sequential Learning. In J. Aguilar A. M. R. Alquezar (Ed.), 13th International Conference of the Catalan Association for Artificial Intelligence (Vol. 220, 193–200).
Abstract: Sequential learning is that discipline of machine learning that deals with dependent data. In this paper, we use the Multi-scale Stacked Sequential Learning approach (MSSL) to solve the task of pixel-wise classification based on contextual information. The main contribution of this work is a shifting technique applied during the testing phase that makes possible, thanks to template images, to classify objects at different sizes. The results show that the proposed method robustly classifies such objects capturing their spatial relationships.
|
|
|
|
Lei Kang, Pau Riba, Mauricio Villegas, Alicia Fornes, & Marçal Rusiñol. (2021). Candidate Fusion: Integrating Language Modelling into a Sequence-to-Sequence Handwritten Word Recognition Architecture. PR - Pattern Recognition, 112, 107790.
Abstract: Sequence-to-sequence models have recently become very popular for tackling
handwritten word recognition problems. However, how to effectively integrate an external language model into such recognizer is still a challenging
problem. The main challenge faced when training a language model is to
deal with the language model corpus which is usually different to the one
used for training the handwritten word recognition system. Thus, the bias
between both word corpora leads to incorrectness on the transcriptions, providing similar or even worse performances on the recognition task. In this
work, we introduce Candidate Fusion, a novel way to integrate an external
language model to a sequence-to-sequence architecture. Moreover, it provides suggestions from an external language knowledge, as a new input to
the sequence-to-sequence recognizer. Hence, Candidate Fusion provides two
improvements. On the one hand, the sequence-to-sequence recognizer has
the flexibility not only to combine the information from itself and the language model, but also to choose the importance of the information provided
by the language model. On the other hand, the external language model
has the ability to adapt itself to the training corpus and even learn the
most commonly errors produced from the recognizer. Finally, by conducting
comprehensive experiments, the Candidate Fusion proves to outperform the
state-of-the-art language models for handwritten word recognition tasks.
|
|
|
|
Jose Manuel Alvarez, Y. LeCun, Theo Gevers, & Antonio Lopez. (2012). Semantic Road Segmentation via Multi-Scale Ensembles of Learned Features. In 12th European Conference on Computer Vision – Workshops and Demonstrations (Vol. 7584, pp. 586–595). LNCS. Springer Berlin Heidelberg.
Abstract: Semantic segmentation refers to the process of assigning an object label (e.g., building, road, sidewalk, car, pedestrian) to every pixel in an image. Common approaches formulate the task as a random field labeling problem modeling the interactions between labels by combining local and contextual features such as color, depth, edges, SIFT or HoG. These models are trained to maximize the likelihood of the correct classification given a training set. However, these approaches rely on hand–designed features (e.g., texture, SIFT or HoG) and a higher computational time required in the inference process.
Therefore, in this paper, we focus on estimating the unary potentials of a conditional random field via ensembles of learned features. We propose an algorithm based on convolutional neural networks to learn local features from training data at different scales and resolutions. Then, diversification between these features is exploited using a weighted linear combination. Experiments on a publicly available database show the effectiveness of the proposed method to perform semantic road scene segmentation in still images. The algorithm outperforms appearance based methods and its performance is similar compared to state–of–the–art methods using other sources of information such as depth, motion or stereo.
Keywords: road detection
|
|
|
|
Jose Luis Gomez, Gabriel Villalonga, & Antonio Lopez. (2023). Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models. SENS - Sensors – Special Issue on “Machine Learning for Autonomous Driving Perception and Prediction”, 23(2), 621.
Abstract: Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated labels together with unlabeled real-world images is a promising alternative. This implies to address an unsupervised domain adaptation (UDA) problem. In this paper, we propose a new co-training procedure for synth-to-real UDA of semantic
segmentation models. It consists of a self-training stage, which provides two domain-adapted models, and a model collaboration loop for the mutual improvement of these two models. These models are then used to provide the final semantic segmentation labels (pseudo-labels) for the real-world images. The overall
procedure treats the deep models as black boxes and drives their collaboration at the level of pseudo-labeled target images, i.e., neither modifying loss functions is required, nor explicit feature alignment. We test our proposal on standard synthetic and real-world datasets for on-board semantic segmentation. Our
procedure shows improvements ranging from ∼13 to ∼26 mIoU points over baselines, so establishing new state-of-the-art results.
Keywords: Domain adaptation; semi-supervised learning; Semantic segmentation; Autonomous driving
|
|
|
|
G. de Oliveira, A. Cartas, Marc Bolaños, Mariella Dimiccoli, Xavier Giro, & Petia Radeva. (2016). LEMoRe: A Lifelog Engine for Moments Retrieval at the NTCIR-Lifelog LSAT Task. In 12th NTCIR Conference on Evaluation of Information Access Technologies.
Abstract: Semantic image retrieval from large amounts of egocentric visual data requires to leverage powerful techniques for filling in the semantic gap. This paper introduces LEMoRe, a Lifelog Engine for Moments Retrieval, developed in the context of the Lifelog Semantic Access Task (LSAT) of the the NTCIR-12 challenge and discusses its performance variation on different trials. LEMoRe integrates classical image descriptors with high-level semantic concepts extracted by Convolutional Neural Networks (CNN), powered by a graphic user interface that uses natural language processing. Although this is just a first attempt towards interactive image retrieval from large egocentric datasets and there is a large room for improvement of the system components and the user interface, the structure of the system itself and the way the single components cooperate are very promising.
|
|
|
|
Marwa Dhiaf, Mohamed Ali Souibgui, Kai Wang, Yuyang Liu, Yousri Kessentini, Alicia Fornes, et al. (2023). CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition.
Abstract: Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, where data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance on English, Italian and Russian scripts, whilst adding only a few parameters per task. The code and trained models will be publicly available.
|
|
|
|
Kai Wang, Fei Yang, & Joost Van de Weijer. (2022). Attention Distillation: self-supervised vision transformer students need more guidance. In 33rd British Machine Vision Conference.
Abstract: Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill knowledge from one self-supervised ViT to another has not yet been explored. Moreover, the existing self-supervised knowledge distillation (SSKD) methods focus on ConvNet based architectures are suboptimal for ViT knowledge distillation. In this paper, we study knowledge distillation of self-supervised vision transformers (ViT-SSKD). We show that directly distilling information from the crucial attention mechanism from teacher to student can significantly narrow the performance gap between both. In experiments on ImageNet-Subset and ImageNet-1K, we show that our method AttnDistill outperforms existing self-supervised knowledge distillation (SSKD) methods and achieves state-of-the-art k-NN accuracy compared with self-supervised learning (SSL) methods learning from scratch (with the ViT-S model). We are also the first to apply the tiny ViT-T model on self-supervised learning. Moreover, AttnDistill is independent of self-supervised learning algorithms, it can be adapted to ViT based SSL methods to improve the performance in future research.
|
|
|
|
Nil Ballus, Bhalaji Nagarajan, & Petia Radeva. (2022). Opt-SSL: An Enhanced Self-Supervised Framework for Food Recognition. In 10th Iberian Conference on Pattern Recognition and Image Analysis (Vol. 13256). LNCS.
Abstract: Self-supervised Learning has been showing upbeat performance in several computer vision tasks. The popular contrastive methods make use of a Siamese architecture with different loss functions. In this work, we go deeper into two very recent state of the art frameworks, namely, SimSiam and Barlow Twins. Inspired by them, we propose a new self-supervised learning method we call Opt-SSL that combines both image and feature contrasting. We validate the proposed method on the food recognition task, showing that our proposed framework enables the self-learning networks to learn better visual representations.
Keywords: Self-supervised; Contrastive learning; Food recognition
|
|
|
|
Raul Gomez, Lluis Gomez, Jaume Gibert, & Dimosthenis Karatzas. (2019). Self-Supervised Learning from Web Data for Multimodal Retrieval. In Multi-Modal Scene Understanding Book (pp. 279–306).
Abstract: Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal data. In this work we propose to exploit this free available data to learn a multimodal image and text embedding, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the proposed pipeline can learn from images with associated text without supervision and analyze the semantic structure of the learnt joint image and text embeddingspace. Weperformathoroughanalysisandperformancecomparisonoffivedifferentstateof the art text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text basedimageretrievaltask,andweclearlyoutperformstateoftheartintheMIRFlickrdatasetwhen training in the target data. Further, we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings.
Keywords: self-supervised learning; webly supervised learning; text embeddings; multimodal retrieval; multimodal embedding
|
|
|
|
Marcin Przewiezlikowski, Mateusz Pyla, Bartosz Zielinski, Bartłomiej Twardowski, Jacek Tabor, & Marek Smieja. (2023). Augmentation-aware Self-supervised Learning with Guided Projector.
Abstract: Self-supervised learning (SSL) is a powerful technique for learning robust representations from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo are able to reach quality on par with supervised approaches. However, this invariance may be harmful to solving some downstream tasks which depend on traits affected by augmentations used during pretraining, such as color. In this paper, we propose to foster sensitivity to such characteristics in the representation space by modifying the projector network, a common component of self-supervised architectures. Specifically, we supplement the projector with information about augmentations applied to images. In order for the projector to take advantage of this auxiliary conditioning when solving the SSL task, the feature extractor learns to preserve the augmentation information in its representations. Our approach, coined Conditional Augmentation-aware Self-supervised Learning (CASSLE), is directly applicable to typical joint-embedding SSL methods regardless of their objective functions. Moreover, it does not require major changes in the network architecture or prior knowledge of downstream tasks. In addition to an analysis of sensitivity towards different data augmentations, we conduct a series of experiments, which show that CASSLE improves over various SSL methods, reaching state-of-the-art performance in multiple downstream tasks.
|
|
|
|
Antonio Hernandez, Carlo Gatta, Sergio Escalera, Laura Igual, Victoria Martin-Yuste, Manel Sabate, et al. (2012). Accurate coronary centerline extraction, caliber estimation and catheter detection in angiographies. TITB - IEEE Transactions on Information Technology in Biomedicine, 16(6), 1332–1340.
Abstract: Segmentation of coronary arteries in X-Ray angiography is a fundamental tool to evaluate arterial diseases and choose proper coronary treatment. The accurate segmentation of coronary arteries has become an important topic for the registration of different modalities which allows physicians rapid access to different medical imaging information from Computed Tomography (CT) scans or Magnetic Resonance Imaging (MRI). In this paper, we propose an accurate fully automatic algorithm based on Graph-cuts for vessel centerline extraction, caliber estimation, and catheter detection. Vesselness, geodesic paths, and a new multi-scale edgeness map are combined to customize the Graph-cuts approach to the segmentation of tubular structures, by means of a global optimization of the Graph-cuts energy function. Moreover, a novel supervised learning methodology that integrates local and contextual information is proposed for automatic catheter detection. We evaluate the method performance on three datasets coming from different imaging systems. The method performs as good as the expert observer w.r.t. centerline detection and caliber estimation. Moreover, the method discriminates between arteries and catheter with an accuracy of 96.5%, sensitivity of 72%, and precision of 97.4%.
|
|
|
|
Lluis Pere de las Heras, Joan Mas, Gemma Sanchez, & Ernest Valveny. (2011). Wall Patch-Based Segmentation in Architectural Floorplans. In 11th International Conference on Document Analysis and Recognition (pp. 1270–1274).
Abstract: Segmentation of architectural floor plans is a challenging task, mainly because of the large variability in the notation between different plans. In general, traditional techniques, usually based on analyzing and grouping structural primitives obtained by vectorization, are only able to handle a reduced range of similar notations. In this paper we propose an alternative patch-based segmentation approach working at pixel level, without need of vectorization. The image is divided into a set of patches and a set of features is extracted for every patch. Then, each patch is assigned to a visual word of a previously learned vocabulary and given a probability of belonging to each class of objects. Finally, a post-process assigns the final label for every pixel. This approach has been applied to the detection of walls on two datasets of architectural floor plans with different notations, achieving high accuracy rates.
|
|
|
|
Debora Gil, Carles Sanchez, Agnes Borras, Marta Diez-Ferrer, & Antoni Rosell. (2019). Segmentation of Distal Airways using Structural Analysis. Plos - PloS one, 14(12).
Abstract: Segmentation of airways in Computed Tomography (CT) scans is a must for accurate support of diagnosis and intervention of many pulmonary disorders. In particular, lung cancer diagnosis would benefit from segmentations reaching most distal airways. We present a method that combines descriptors of bronchi local appearance and graph global structural analysis to fine-tune thresholds on the descriptors adapted for each bronchial level. We have compared our method to the top performers of the EXACT09 challenge and to a commercial software for biopsy planning evaluated in an own-collected data-base of high resolution CT scans acquired under different breathing conditions. Results on EXACT09 data show that our method provides a high leakage reduction with minimum loss in airway detection. Results on our data-base show the reliability across varying breathing conditions and a competitive performance for biopsy planning compared to a commercial solution.
|
|
|
|
Jose Carlos Rubio, Joan Serrat, & Antonio Lopez. (2012). Video Co-segmentation. In 11th Asian Conference on Computer Vision (Vol. 7725, pp. 13–24). LNCS. Springer Berlin Heidelberg.
Abstract: Segmentation of a single image is in general a highly underconstrained problem. A frequent approach to solve it is to somehow provide prior knowledge or constraints on how the objects of interest look like (in terms of their shape, size, color, location or structure). Image co-segmentation trades the need for such knowledge for something much easier to obtain, namely, additional images showing the object from other viewpoints. Now the segmentation problem is posed as one of differentiating the similar object regions in all the images from the more varying background. In this paper, for the first time, we extend this approach to video segmentation: given two or more video sequences showing the same object (or objects belonging to the same class) moving in a similar manner, we aim to outline its region in all the frames. In addition, the method works in an unsupervised manner, by learning to segment at testing time. We compare favorably with two state-of-the-art methods on video segmentation and report results on benchmark videos.
|
|
|
|
Ivan Huerta, Michael Holte, Thomas B. Moeslund, & Jordi Gonzalez. (2009). Detection and Removal of Chromatic Moving Shadows in Surveillance Scenarios. In 12th International Conference on Computer Vision (pp. 1499–1506).
Abstract: Segmentation in the surveillance domain has to deal with shadows to avoid distortions when detecting moving objects. Most segmentation approaches dealing with shadow detection are typically restricted to penumbra shadows. Therefore, such techniques cannot cope well with umbra shadows. Consequently, umbra shadows are usually detected as part of moving objects. In this paper we present a novel technique based on gradient and colour models for separating chromatic moving cast shadows from detected moving objects. Firstly, both a chromatic invariant colour cone model and an invariant gradient model are built to perform automatic segmentation while detecting potential shadows. In a second step, regions corresponding to potential shadows are grouped by considering “a bluish effect” and an edge partitioning. Lastly, (i) temporal similarities between textures and (ii) spatial similarities between chrominance angle and brightness distortions are analysed for all potential shadow regions in order to finally identify umbra shadows. Unlike other approaches, our method does not make any a-priori assumptions about camera location, surface geometries, surface textures, shapes and types of shadows, objects, and background. Experimental results show the performance and accuracy of our approach in different shadowed materials and illumination conditions.
|
|
