| Home | << 1 2 3 4 5 6 7 8 9 10 >> |
|
| Records | |||||
|---|---|---|---|---|---|
Author  |
Fei Yang; Yaxing Wang; Luis Herranz; Yongmei Cheng; Mikhail Mozerov | ||||
| Title | A Novel Framework for Image-to-image Translation and Image Compression | Type | Journal Article | ||
| Year | 2022 | Publication | Neurocomputing | Abbreviated Journal | NEUCOM |
| Volume | 508 | Issue | Pages | 58-70 | |
| Keywords | |||||
| Abstract | Data-driven paradigms using machine learning are becoming ubiquitous in image processing and communications. In particular, image-to-image (I2I) translation is a generic and widely used approach to image processing problems, such as image synthesis, style transfer, and image restoration. At the same time, neural image compression has emerged as a data-driven alternative to traditional coding approaches in visual communications. In this paper, we study the combination of these two paradigms into a joint I2I compression and translation framework, focusing on multi-domain image synthesis. We first propose distributed I2I translation by integrating quantization and entropy coding into an I2I translation framework (i.e. I2Icodec). In practice, the image compression functionality (i.e. autoencoding) is also desirable, requiring to deploy alongside I2Icodec a regular image codec. Thus, we further propose a unified framework that allows both translation and autoencoding capabilities in a single codec. Adaptive residual blocks conditioned on the translation/compression mode provide flexible adaptation to the desired functionality. The experiments show promising results in both I2I translation and image compression using a single model. | ||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | LAMP | Approved | no | ||
| Call Number | Admin @ si @ YWH2022 | Serial | 3679 | ||
| Permanent link to this record | |||||
| Author |
Francesco Pelosin; Saurav Jha; Andrea Torsello; Bogdan Raducanu; Joost Van de Weijer | ||||
| Title | Towards exemplar-free continual learning in vision transformers: an account of attention, functional and weight regularization | Type | Conference Article | ||
| Year | 2022 | Publication | IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | Learning systems; Weight measurement; Image recognition; Surgery; Benchmark testing; Transformers; Stability analysis | ||||
| Abstract | In this paper, we investigate the continual learning of Vision Transformers (ViT) for the challenging exemplar-free scenario, with special focus on how to efficiently distill the knowledge of its crucial self-attention mechanism (SAM). Our work takes an initial step towards a surgical investigation of SAM for designing coherent continual learning methods in ViTs. We first carry out an evaluation of established continual learning regularization techniques. We then examine the effect of regularization when applied to two key enablers of SAM: (a) the contextualized embedding layers, for their ability to capture well-scaled representations with respect to the values, and (b) the prescaled attention maps, for carrying value-independent global contextual information. We depict the perks of each distilling strategy on two image recognition benchmarks (CIFAR100 and ImageNet-32) – while (a) leads to a better overall accuracy, (b) helps enhance the rigidity by maintaining competitive performances. Furthermore, we identify the limitation imposed by the symmetric nature of regularization losses. To alleviate this, we propose an asymmetric variant and apply it to the pooled output distillation (POD) loss adapted for ViTs. Our experiments confirm that introducing asymmetry to POD boosts its plasticity while retaining stability across (a) and (b). Moreover, we acknowledge low forgetting measures for all the compared methods, indicating that ViTs might be naturally inclined continual learners. 1 | ||||
| Address | New Orleans; USA; June 2022 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | CVPRW | ||
| Notes | LAMP; 600.147 | Approved | no | ||
| Call Number | Admin @ si @ PJT2022 | Serial | 3784 | ||
| Permanent link to this record | |||||
| Author |
German Barquero; Johnny Nuñez; Sergio Escalera; Zhen Xu; Wei-Wei Tu; Isabelle Guyon | ||||
| Title | Didn’t see that coming: a survey on non-verbal social human behavior forecasting | Type | Conference Article | ||
| Year | 2022 | Publication | Understanding Social Behavior in Dyadic and Small Group Interactions | Abbreviated Journal | |
| Volume | 173 | Issue | Pages | 139-178 | |
| Keywords | |||||
| Abstract | Non-verbal social human behavior forecasting has increasingly attracted the interest of the research community in recent years. Its direct applications to human-robot interaction and socially-aware human motion generation make it a very attractive field. In this survey, we define the behavior forecasting problem for multiple interactive agents in a generic way that aims at unifying the fields of social signals prediction and human motion forecasting, traditionally separated. We hold that both problem formulations refer to the same conceptual problem, and identify many shared fundamental challenges: future stochasticity, context awareness, history exploitation, etc. We also propose a taxonomy that comprises
methods published in the last 5 years in a very informative way and describes the current main concerns of the community with regard to this problem. In order to promote further research on this field, we also provide a summarized and friendly overview of audiovisual datasets featuring non-acted social interactions. Finally, we describe the most common metrics used in this task and their particular issues. |
||||
| Address | Virtual; June 2022 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | PMLR | ||
| Notes | HuPBA; no proj | Approved | no | ||
| Call Number | Admin @ si @ BNE2022 | Serial | 3766 | ||
| Permanent link to this record | |||||
| Author |
Giacomo Magnifico; Beata Megyesi; Mohamed Ali Souibgui; Jialuo Chen; Alicia Fornes | ||||
| Title | Lost in Transcription of Graphic Signs in Ciphers | Type | Conference Article | ||
| Year | 2022 | Publication | International Conference on Historical Cryptology (HistoCrypt 2022) | Abbreviated Journal | |
| Volume | Issue | Pages | 153-158 | ||
| Keywords | transcription of ciphers; hand-written text recognition of symbols; graphic signs | ||||
| Abstract | Hand-written Text Recognition techniques with the aim to automatically identify and transcribe hand-written text have been applied to historical sources including ciphers. In this paper, we compare the performance of two machine learning architectures, an unsupervised method based on clustering and a deep learning method with few-shot learning. Both models are tested on seen and unseen data from historical ciphers with different symbol sets consisting of various types of graphic signs. We compare the models and highlight their differences in performance, with their advantages and shortcomings. | ||||
| Address | Amsterdam, Netherlands, June 20-22, 2022 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | HystoCrypt | ||
| Notes | DAG; 600.121; 600.162; 602.230; 600.140 | Approved | no | ||
| Call Number | Admin @ si @ MBS2022 | Serial | 3731 | ||
| Permanent link to this record | |||||
| Author |
Giuseppe De Gregorio; Sanket Biswas; Mohamed Ali Souibgui; Asma Bensalah; Josep Llados; Alicia Fornes; Angelo Marcelli | ||||
| Title | A Few Shot Multi-representation Approach for N-Gram Spotting in Historical Manuscripts | Type | Conference Article | ||
| Year | 2022 | Publication | Frontiers in Handwriting Recognition. International Conference on Frontiers in Handwriting Recognition (ICFHR2022) | Abbreviated Journal | |
| Volume | 13639 | Issue | Pages | 3-12 | |
| Keywords | N-gram spotting; Few-shot learning; Multimodal understanding; Historical handwritten collections | ||||
| Abstract | Despite recent advances in automatic text recognition, the performance remains moderate when it comes to historical manuscripts. This is mainly because of the scarcity of available labelled data to train the data-hungry Handwritten Text Recognition (HTR) models. The Keyword Spotting System (KWS) provides a valid alternative to HTR due to the reduction in error rate, but it is usually limited to a closed reference vocabulary. In this paper, we propose a few-shot learning paradigm for spotting sequences of a few characters (N-gram) that requires a small amount of labelled training data. We exhibit that recognition of important n-grams could reduce the system’s dependency on vocabulary. In this case, an out-of-vocabulary (OOV) word in an input handwritten line image could be a sequence of n-grams that belong to the lexicon. An extensive experimental evaluation of our proposed multi-representation approach was carried out on a subset of Bentham’s historical manuscript collections to obtain some really promising results in this direction. | ||||
| Address | December 04 – 07, 2022; Hyderabad, India | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | ICFHR | ||
| Notes | DAG; 600.121; 600.162; 602.230; 600.140 | Approved | no | ||
| Call Number | Admin @ si @ GBS2022 | Serial | 3733 | ||
| Permanent link to this record | |||||
| Author |
Guillem Martinez; Maya Aghaei; Martin Dijkstra; Bhalaji Nagarajan; Femke Jaarsma; Jaap van de Loosdrecht; Petia Radeva; Klaas Dijkstra | ||||
| Title | Hyper-Spectral Imaging for Overlapping Plastic Flakes Segmentation | Type | Conference Article | ||
| Year | 2022 | Publication | 47th International Conference on Acoustics, Speech, and Signal Processing | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | Hyper-spectral imaging; plastic sorting; multi-label segmentation; bitfield encoding | ||||
| Abstract | In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. DCNGAN is also adaptive to the quantization parameters (QPs). Compared with optical flows, deformable convolutions are more effective and efficient to align frames. Deformable convolutions can operate on multiple frames, thus leveraging more temporal information, which is beneficial for enhancing the perceptual quality of compressed videos. Instead of aligning frames in a pairwise manner, the deformable convolution can process multiple frames simultaneously, which leads to lower computational complexity. Experimental results demonstrate that the proposed DCNGAN outperforms other state-of-the-art compressed video quality enhancement algorithms. | ||||
| Address | Singapore; May 2022 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | ICASSP | ||
| Notes | MILAB; no proj | Approved | no | ||
| Call Number | Admin @ si @ MAD2022 | Serial | 3767 | ||
| Permanent link to this record | |||||
| Author |
Guillermo Torres; Sonia Baeza; Carles Sanchez; Ignasi Guasch; Antoni Rosell; Debora Gil | ||||
| Title | An Intelligent Radiomic Approach for Lung Cancer Screening | Type | Journal Article | ||
| Year | 2022 | Publication | Applied Sciences | Abbreviated Journal | APPLSCI |
| Volume | 12 | Issue | 3 | Pages | 1568 |
| Keywords | Lung cancer; Early diagnosis; Screening; Neural networks; Image embedding; Architecture optimization | ||||
| Abstract | The efficiency of lung cancer screening for reducing mortality is hindered by the high rate of false positives. Artificial intelligence applied to radiomics could help to early discard benign cases from the analysis of CT scans. The available amount of data and the fact that benign cases are a minority, constitutes a main challenge for the successful use of state of the art methods (like deep learning), which can be biased, over-fitted and lack of clinical reproducibility. We present an hybrid approach combining the potential of radiomic features to characterize nodules in CT scans and the generalization of the feed forward networks. In order to obtain maximal reproducibility with minimal training data, we propose an embedding of nodules based on the statistical significance of radiomic features for malignancy detection. This representation space of lesions is the input to a feed
forward network, which architecture and hyperparameters are optimized using own-defined metrics of the diagnostic power of the whole system. Results of the best model on an independent set of patients achieve 100% of sensitivity and 83% of specificity (AUC = 0.94) for malignancy detection. |
||||
| Address | Jan 2022 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | IAM; 600.139; 600.145 | Approved | no | ||
| Call Number | Admin @ si @ TBS2022 | Serial | 3699 | ||
| Permanent link to this record | |||||
| Author |
Hector Laria Mantecon; Yaxing Wang; Joost Van de Weijer; Bogdan Raducanu | ||||
| Title | Transferring Unconditional to Conditional GANs With Hyper-Modulation | Type | Conference Article | ||
| Year | 2022 | Publication | IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | GANs have matured in recent years and are able to generate high-resolution, realistic images. However, the computational resources and the data required for the training of high-quality GANs are enormous, and the study of transfer learning of these models is therefore an urgent topic. Many of the available high-quality pretrained GANs are unconditional (like StyleGAN). For many applications, however, conditional GANs are preferable, because they provide more control over the generation process, despite often suffering more training difficulties. Therefore, in this paper, we focus on transferring from high-quality pretrained unconditional GANs to conditional GANs. This requires architectural adaptation of the pretrained GAN to perform the conditioning. To this end, we propose hyper-modulated generative networks that allow for shared and complementary supervision. To prevent the additional weights of the hypernetwork to overfit, with subsequent mode collapse on small target domains, we introduce a self-initialization procedure that does not require any real data to initialize the hypernetwork parameters. To further improve the sample efficiency of the transfer, we apply contrastive learning in the discriminator, which effectively works on very limited batch sizes. In extensive experiments, we validate the efficiency of the hypernetworks, self-initialization and contrastive loss for knowledge transfer on standard benchmarks. | ||||
| Address | New Orleans; USA; June 2022 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | CVPRW | ||
| Notes | LAMP; 600.147; 602.200 | Approved | no | ||
| Call Number | LWW2022a | Serial | 3785 | ||
| Permanent link to this record | |||||
| Author |
Henry Velesaca; Patricia Suarez; Angel Sappa; Dario Carpio; Rafael E. Rivadeneira; Angel Sanchez | ||||
| Title | Review on Common Techniques for Urban Environment Video Analytics | Type | Conference Article | ||
| Year | 2022 | Publication | Anais do III Workshop Brasileiro de Cidades Inteligentes | Abbreviated Journal | |
| Volume | Issue | Pages | 107-118 | ||
| Keywords | Video Analytics; Review; Urban Environments; Smart Cities | ||||
| Abstract | This work compiles the different computer vision-based approaches
from the state-of-the-art intended for video analytics in urban environments. The manuscript groups the different approaches according to the typical modules present in video analysis, including image preprocessing, object detection, classification, and tracking. This proposed pipeline serves as a basic guide to representing these most representative approaches in this topic of video analysis that will be addressed in this work. Furthermore, the manuscript is not intended to be an exhaustive review of the most advanced approaches, but only a list of common techniques proposed to address recurring problems in this field. |
||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | WBCI | ||
| Notes | MSIAU; 601.349 | Approved | no | ||
| Call Number | Admin @ si @ VSS2022 | Serial | 3773 | ||
| Permanent link to this record | |||||
| Author |
Henry Velesaca; Patricia Suarez; Dario Carpio; Rafael E. Rivadeneira; Angel Sanchez; Angel Morera | ||||
| Title | Video Analytics in Urban Environments: Challenges and Approaches | Type | Book Chapter | ||
| Year | 2022 | Publication | ICT Applications for Smart Cities | Abbreviated Journal | |
| Volume | 224 | Issue | Pages | 101-121 | |
| Keywords | |||||
| Abstract | This chapter reviews state-of-the-art approaches generally present in the pipeline of video analytics on urban scenarios. A typical pipeline is used to cluster approaches in the literature, including image preprocessing, object detection, object classification, and object tracking modules. Then, a review of recent approaches for each module is given. Additionally, applications and datasets generally used for training and evaluating the performance of these approaches are included. This chapter does not pretend to be an exhaustive review of state-of-the-art video analytics in urban environments but rather an illustration of some of the different recent contributions. The chapter concludes by presenting current trends in video analytics in the urban scenario field. | ||||
| Address | September 2022 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Springer | Place of Publication | Editor | ||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | ISRL | ||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 978-3-031-06306-0 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | MSIAU; MACO | Approved | no | ||
| Call Number | Admin @ si @ VSC2022 | Serial | 3811 | ||
| Permanent link to this record | |||||
| Author |
Hugo Bertiche; Meysam Madadi; Sergio Escalera | ||||
| Title | Neural Cloth Simulation | Type | Journal Article | ||
| Year | 2022 | Publication | ACM Transactions on Graphics | Abbreviated Journal | ACMTGraph |
| Volume | 41 | Issue | 6 | Pages | 1-14 |
| Keywords | |||||
| Abstract | We present a general framework for the garment animation problem through unsupervised deep learning inspired in physically based simulation. Existing trends in the literature already explore this possibility. Nonetheless, these approaches do not handle cloth dynamics. Here, we propose the first methodology able to learn realistic cloth dynamics unsupervisedly, and henceforth, a general formulation for neural cloth simulation. The key to achieve this is to adapt an existing optimization scheme for motion from simulation based methodologies to deep learning. Then, analyzing the nature of the problem, we devise an architecture able to automatically disentangle static and dynamic cloth subspaces by design. We will show how this improves model performance. Additionally, this opens the possibility of a novel motion augmentation technique that greatly improves generalization. Finally, we show it also allows to control the level of motion in the predictions. This is a useful, never seen before, tool for artists. We provide of detailed analysis of the problem to establish the bases of neural cloth simulation and guide future research into the specifics of this domain.
ACM Transactions on GraphicsVolume 41Issue 6December 2022 Article No.: 220pp 1– |
||||
| Address | Dec 2022 | ||||
| Corporate Author | Thesis | ||||
| Publisher | ACM | Place of Publication | Editor | ||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | Approved | no | |||
| Call Number | Admin @ si @ BME2022b | Serial | 3779 | ||
| Permanent link to this record | |||||
| Author |
Hugo Jair Escalante; Heysem Kaya; Albert Ali Salah; Sergio Escalera; Yagmur Gucluturk; Umut Guçlu; Xavier Baro; Isabelle Guyon; Julio C. S. Jacques Junior; Meysam Madadi; Stephane Ayache; Evelyne Viegas; Furkan Gurpinar; Achmadnoer Sukma Wicaksana; Cynthia Liem; Marcel A. J. Van Gerven; Rob Van Lier | ||||
| Title | Modeling, Recognizing, and Explaining Apparent Personality from Videos | Type | Journal Article | ||
| Year | 2022 | Publication | IEEE Transactions on Affective Computing | Abbreviated Journal | TAC |
| Volume | 13 | Issue | 2 | Pages | 894-911 |
| Keywords | |||||
| Abstract | Explainability and interpretability are two critical aspects of decision support systems. Despite their importance, it is only recently that researchers are starting to explore these aspects. This paper provides an introduction to explainability and interpretability in the context of apparent personality recognition. To the best of our knowledge, this is the first effort in this direction. We describe a challenge we organized on explainability in first impressions analysis from video. We analyze in detail the newly introduced data set, evaluation protocol, proposed solutions and summarize the results of the challenge. We investigate the issue of bias in detail. Finally, derived from our study, we outline research opportunities that we foresee will be relevant in this area in the near future. | ||||
| Address | 1 April-June 2022 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | HuPBA; no menciona | Approved | no | ||
| Call Number | Admin @ si @ EKS2022 | Serial | 3406 | ||
| Permanent link to this record | |||||
| Author |
Iban Berganzo-Besga; Hector A. Orengo; Felipe Lumbreras; Paloma Aliende; Monica N. Ramsey | ||||
| Title | Automated detection and classification of multi-cell Phytoliths using Deep Learning-Based Algorithms | Type | Journal Article | ||
| Year | 2022 | Publication | Journal of Archaeological Science | Abbreviated Journal | JArchSci |
| Volume | 148 | Issue | Pages | 105654 | |
| Keywords | |||||
| Abstract | This paper presents an algorithm for automated detection and classification of multi-cell phytoliths, one of the major components of many archaeological and paleoenvironmental deposits. This identification, based on phytolith wave pattern, is made using a pretrained VGG19 deep learning model. This approach has been tested in three key phytolith genera for the study of agricultural origins in Near East archaeology: Avena, Hordeum and Triticum. Also, this classification has been validated at species-level using Triticum boeoticum and dicoccoides images. Due to the diversity of microscopes, cameras and chemical treatments that can influence images of phytolith slides, three types of data augmentation techniques have been implemented: rotation of the images at 45-degree angles, random colour and brightness jittering, and random blur/sharpen. The implemented workflow has resulted in an overall accuracy of 93.68% for phytolith genera, improving previous attempts. The algorithm has also demonstrated its potential to automatize the classification of phytoliths species with an overall accuracy of 100%. The open code and platforms employed to develop the algorithm assure the method's accessibility, reproducibility and reusability. | ||||
| Address | December 2022 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | MSIAU; MACO; 600.167 | Approved | no | ||
| Call Number | Admin @ si @ BOL2022 | Serial | 3753 | ||
| Permanent link to this record | |||||
| Author |
Idoia Ruiz | ||||
| Title | Deep Metric Learning for re-identification, tracking and hierarchical novelty detection | Type | Book Whole | ||
| Year | 2022 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| 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. | ||||
| Address | July, 2022 | ||||
| Corporate Author | Thesis | Ph.D. thesis | |||
| Publisher | Place of Publication | Editor | Joan Serrat | ||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 978-84-124793-4-8 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | ADAS | Approved | no | ||
| Call Number | Admin @ si @ Rui2022 | Serial | 3717 | ||
| Permanent link to this record | |||||
| Author |
Idoia Ruiz; Joan Serrat | ||||
| Title | Hierarchical Novelty Detection for Traffic Sign Recognition | Type | Journal Article | ||
| Year | 2022 | Publication | Sensors | Abbreviated Journal | SENS |
| Volume | 22 | Issue | 12 | Pages | 4389 |
| Keywords | Novelty detection; hierarchical classification; deep learning; traffic sign recognition; autonomous driving; computer vision | ||||
| Abstract | Recent works have made significant progress in novelty detection, i.e., the problem of detecting samples of novel classes, never seen during training, while classifying those that belong to known classes. However, the only information this task provides about novel samples is that they are unknown. In this work, we leverage hierarchical taxonomies of classes to provide informative outputs for samples of novel classes. We predict their closest class in the taxonomy, i.e., its parent class. We address this problem, known as hierarchical novelty detection, by proposing a novel loss, namely Hierarchical Cosine Loss that is designed to learn class prototypes along with an embedding of discriminative features consistent with the taxonomy. We apply it to traffic sign recognition, where we predict the parent class semantics for new types of traffic signs. Our model beats state-of-the art approaches on two large scale traffic sign benchmarks, Mapillary Traffic Sign Dataset (MTSD) and Tsinghua-Tencent 100K (TT100K), and performs similarly on natural images benchmarks (AWA2, CUB). For TT100K and MTSD, our approach is able to detect novel samples at the correct nodes of the hierarchy with 81% and 36% of accuracy, respectively, at 80% known class accuracy. | ||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | ADAS; 600.154 | Approved | no | ||
| Call Number | Admin @ si @ RuS2022 | Serial | 3684 | ||
| Permanent link to this record | |||||