|
Records |
Links |
|
Author |
Shiqi Yang; Yaxing Wang; Joost Van de Weijer; Luis Herranz |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Unsupervised Domain Adaptation without Source Data by Casting a BAIT |
Type |
Miscellaneous |
|
Year |
2020 |
Publication |
Arxiv |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
arXiv:2010.12427
Unsupervised domain adaptation (UDA) aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain. Existing UDA methods require access to source data during adaptation, which may not be feasible in some real-world applications. In this paper, we address the source-free unsupervised domain adaptation (SFUDA) problem, where only the source model is available during the adaptation. We propose a method named BAIT to address SFUDA. Specifically, given only the source model, with the source classifier head fixed, we introduce a new learnable classifier. When adapting to the target domain, class prototypes of the new added classifier will act as a bait. They will first approach the target features which deviate from prototypes of the source classifier due to domain shift. Then those target features are pulled towards the corresponding prototypes of the source classifier, thus achieving feature alignment with the source classifier in the absence of source data. Experimental results show that the proposed method achieves state-of-the-art performance on several benchmark datasets compared with existing UDA and SFUDA methods. |
|
|
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; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ YWW2020 |
Serial |
3539 |
|
Permanent link to this record |
|
|
|
|
Author |
Shiqi Yang; Kai Wang; Luis Herranz; Joost Van de Weijer |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Simple and effective localized attribute representations for zero-shot learning |
Type |
Miscellaneous |
|
Year |
2020 |
Publication |
Arxiv |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
arXiv:2006.05938
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their semantic descriptions. Some recent papers have shown the importance of localized features together with fine-tuning the feature extractor to obtain discriminative and transferable features. However, these methods require complex attention or part detection modules to perform explicit localization in the visual space. In contrast, in this paper we propose localizing representations in the semantic/attribute space, with a simple but effective pipeline where localization is implicit. Focusing on attribute representations, we show that our method obtains state-of-the-art performance on CUB and SUN datasets, and also achieves competitive results on AWA2 dataset, outperforming generally more complex methods with explicit localization in the visual space. Our method can be implemented easily, which can be used as a new baseline for zero shot-learning. In addition, our localized representations are highly interpretable as attribute-specific heatmaps. |
|
|
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; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ YWH2020 |
Serial |
3542 |
|
Permanent link to this record |
|
|
|
|
Author |
Kai Wang; Luis Herranz; Joost Van de Weijer |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Continual learning in cross-modal retrieval |
Type |
Conference Article |
|
Year |
2021 |
Publication |
2nd CLVISION workshop |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
3628-3638 |
|
|
Keywords |
|
|
|
Abstract |
Multimodal representations and continual learning are two areas closely related to human intelligence. The former considers the learning of shared representation spaces where information from different modalities can be compared and integrated (we focus on cross-modal retrieval between language and visual representations). The latter studies how to prevent forgetting a previously learned task when learning a new one. While humans excel in these two aspects, deep neural networks are still quite limited. In this paper, we propose a combination of both problems into a continual cross-modal retrieval setting, where we study how the catastrophic interference caused by new tasks impacts the embedding spaces and their cross-modal alignment required for effective retrieval. We propose a general framework that decouples the training, indexing and querying stages. We also identify and study different factors that may lead to forgetting, and propose tools to alleviate it. We found that the indexing stage pays an important role and that simply avoiding reindexing the database with updated embedding networks can lead to significant gains. We evaluated our methods in two image-text retrieval datasets, obtaining significant gains with respect to the fine tuning baseline. |
|
|
Address |
Virtual; June 2021 |
|
|
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; 600.120; 600.141; 600.147; 601.379 |
Approved |
no |
|
|
Call Number |
Admin @ si @ WHW2021 |
Serial |
3566 |
|
Permanent link to this record |
|
|
|
|
Author |
Vincenzo Lomonaco; Lorenzo Pellegrini; Andrea Cossu; Antonio Carta; Gabriele Graffieti; Tyler L. Hayes; Matthias De Lange; Marc Masana; Jary Pomponi; Gido van de Ven; Martin Mundt; Qi She; Keiland Cooper; Jeremy Forest; Eden Belouadah; Simone Calderara; German I. Parisi; Fabio Cuzzolin; Andreas Tolias; Simone Scardapane; Luca Antiga; Subutai Amhad; Adrian Popescu; Christopher Kanan; Joost Van de Weijer; Tinne Tuytelaars; Davide Bacciu; Davide Maltoni |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Avalanche: an End-to-End Library for Continual Learning |
Type |
Conference Article |
|
Year |
2021 |
Publication |
34th IEEE Conference on Computer Vision and Pattern Recognition Workshops |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
3595-3605 |
|
|
Keywords |
|
|
|
Abstract |
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms. |
|
|
Address |
Virtual; June 2021 |
|
|
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; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ LPC2021 |
Serial |
3567 |
|
Permanent link to this record |
|
|
|
|
Author |
Mikel Menta; Adriana Romero; Joost Van de Weijer |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Learning to adapt class-specific features across domains for semantic segmentation |
Type |
Miscellaneous |
|
Year |
2020 |
Publication |
Arxiv |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
arXiv:2001.08311
Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on a target domain without requiring any training annotations in this domain. The great majority of existing domain adaptation models rely on image translation networks, which often contain a huge amount of domain-specific parameters. Additionally, the feature adaptation step often happens globally, at a coarse level, hindering its applicability to tasks such as semantic segmentation, where details are of crucial importance to provide sharp results. In this thesis, we present a novel architecture, which learns to adapt features across domains by taking into account per class information. To that aim, we design a conditional pixel-wise discriminator network, whose output is conditioned on the segmentation masks. Moreover, following recent advances in image translation, we adopt the recently introduced StarGAN architecture as image translation backbone, since it is able to perform translations across multiple domains by means of a single generator network. Preliminary results on a segmentation task designed to assess the effectiveness of the proposed approach highlight the potential of the model, improving upon strong baselines and alternative designs. |
|
|
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; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ MRW2020 |
Serial |
3545 |
|
Permanent link to this record |
|
|
|
|
Author |
Idoia Ruiz; Lorenzo Porzi; Samuel Rota Bulo; Peter Kontschieder; Joan Serrat |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Weakly Supervised Multi-Object Tracking and Segmentation |
Type |
Conference Article |
|
Year |
2021 |
Publication |
IEEE Winter Conference on Applications of Computer Vision Workshops |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
125-133 |
|
|
Keywords |
|
|
|
Abstract |
We introduce the problem of weakly supervised MultiObject Tracking and Segmentation, i.e. joint weakly supervised instance segmentation and multi-object tracking, in which we do not provide any kind of mask annotation.
To address it, we design a novel synergistic training strategy by taking advantage of multi-task learning, i.e. classification and tracking tasks guide the training of the unsupervised instance segmentation. For that purpose, we extract weak foreground localization information, provided by
Grad-CAM heatmaps, to generate a partial ground truth to learn from. Additionally, RGB image level information is employed to refine the mask prediction at the edges of the
objects. We evaluate our method on KITTI MOTS, the most representative benchmark for this task, reducing the performance gap on the MOTSP metric between the fully supervised and weakly supervised approach to just 12% and 12.7 % for cars and pedestrians, respectively. |
|
|
Address |
Virtual; January 2021 |
|
|
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 |
WACVW |
|
|
Notes |
ADAS; 600.118; 600.124 |
Approved |
no |
|
|
Call Number |
Admin @ si @ RPR2021 |
Serial |
3548 |
|
Permanent link to this record |
|
|
|
|
Author |
Idoia Ruiz; Joan Serrat |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Rank-based ordinal classification |
Type |
Conference Article |
|
Year |
2020 |
Publication |
25th International Conference on Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
8069-8076 |
|
|
Keywords |
|
|
|
Abstract |
Differently from the regular classification task, in ordinal classification there is an order in the classes. As a consequence not all classification errors matter the same: a predicted class close to the groundtruth one is better than predicting a farther away class. To account for this, most previous works employ loss functions based on the absolute difference between the predicted and groundtruth class labels. We argue that there are many cases in ordinal classification where label values are arbitrary (for instance 1. . . C, being C the number of classes) and thus such loss functions may not be the best choice. We instead propose a network architecture that produces not a single class prediction but an ordered vector, or ranking, of all the possible classes from most to least likely. This is thanks to a loss function that compares groundtruth and predicted rankings of these class labels, not the labels themselves. Another advantage of this new formulation is that we can enforce consistency in the predictions, namely, predicted rankings come from some unimodal vector of scores with mode at the groundtruth class. We compare with the state of the art ordinal classification methods, showing
that ours attains equal or better performance, as measured by common ordinal classification metrics, on three benchmark datasets. Furthermore, it is also suitable for a new task on image aesthetics assessment, i.e. most voted score prediction. Finally, we also apply it to building damage assessment from satellite images, providing an analysis of its performance depending on the degree of imbalance of the dataset. |
|
|
Address |
Virtual; January 2021 |
|
|
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 |
ICPR |
|
|
Notes |
ADAS; 600.118; 600.124 |
Approved |
no |
|
|
Call Number |
Admin @ si @ RuS2020 |
Serial |
3549 |
|
Permanent link to this record |
|
|
|
|
Author |
Guillem Cucurull; Pau Rodriguez; Vacit Oguz Yazici; Josep M. Gonfaus; Xavier Roca; Jordi Gonzalez |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Deep Inference of Personality Traits by Integrating Image and Word Use in Social Networks |
Type |
Miscellaneous |
|
Year |
2018 |
Publication |
Arxiv |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
arXiv:1802.06757
Social media, as a major platform for communication and information exchange, is a rich repository of the opinions and sentiments of 2.3 billion users about a vast spectrum of topics. To sense the whys of certain social user’s demands and cultural-driven interests, however, the knowledge embedded in the 1.8 billion pictures which are uploaded daily in public profiles has just started to be exploited since this process has been typically been text-based. Following this trend on visual-based social analysis, we present a novel methodology based on Deep Learning to build a combined image-and-text based personality trait model, trained with images posted together with words found highly correlated to specific personality traits. So the key contribution here is to explore whether OCEAN personality trait modeling can be addressed based on images, here called MindPics, appearing with certain tags with psychological insights. We found that there is a correlation between those posted images and their accompanying texts, which can be successfully modeled using deep neural networks for personality estimation. The experimental results are consistent with previous cyber-psychology results based on texts or images.
In addition, classification results on some traits show that some patterns emerge in the set of images corresponding to a specific text, in essence to those representing an abstract concept. These results open new avenues of research for further refining the proposed personality model under the supervision of psychology experts. |
|
|
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 |
ISE; 600.098; 600.119 |
Approved |
no |
|
|
Call Number |
Admin @ si @ CRY2018 |
Serial |
3550 |
|
Permanent link to this record |
|
|
|
|
Author |
Pau Rodriguez; Jordi Gonzalez; Josep M. Gonfaus; Xavier Roca |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Towards Visual Personality Questionnaires based on Deep Learning and Social Media |
Type |
Conference Article |
|
Year |
2019 |
Publication |
21st International Conference on Social Influence and Social Psychology |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
April 2019; Tokio; Japan |
|
|
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 |
ICSISP |
|
|
Notes |
ISE; 600.119 |
Approved |
no |
|
|
Call Number |
Admin @ si @ RGG2020 |
Serial |
3554 |
|
Permanent link to this record |
|
|
|
|
Author |
Pau Riba; Andreas Fischer; Josep Llados; Alicia Fornes |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Learning Graph Edit Distance by Graph NeuralNetworks |
Type |
Miscellaneous |
|
Year |
2020 |
Publication |
Arxiv |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies. In this paper, we propose a new framework able to combine the advances on deep metric learning with traditional approximations of the graph edit distance. Hence, we propose an efficient graph distance based on the novel field of geometric deep learning. Our method employs a message passing neural network to capture the graph structure, and thus, leveraging this information for its use on a distance computation. The performance of the proposed graph distance is validated on two different scenarios. On the one hand, in a graph retrieval of handwritten words~\ie~keyword spotting, showing its superior performance when compared with (approximate) graph edit distance benchmarks. On the other hand, demonstrating competitive results for graph similarity learning when compared with the current state-of-the-art on a recent benchmark dataset. |
|
|
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 |
DAG; 600.121; 600.140; 601.302 |
Approved |
no |
|
|
Call Number |
Admin @ si @ RFL2020 |
Serial |
3555 |
|
Permanent link to this record |
|
|
|
|
Author |
Klara Janousckova; Jiri Matas; Lluis Gomez; Dimosthenis Karatzas |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Text Recognition – Real World Data and Where to Find Them |
Type |
Conference Article |
|
Year |
2020 |
Publication |
25th International Conference on Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
4489-4496 |
|
|
Keywords |
|
|
|
Abstract |
We present a method for exploiting weakly annotated images to improve text extraction pipelines. The approach uses an arbitrary end-to-end text recognition system to obtain text region proposals and their, possibly erroneous, transcriptions. The method includes matching of imprecise transcriptions to weak annotations and an edit distance guided neighbourhood search. It produces nearly error-free, localised instances of scene text, which we treat as “pseudo ground truth” (PGT). The method is applied to two weakly-annotated datasets. Training with the extracted PGT consistently improves the accuracy of a state of the art recognition model, by 3.7% on average, across different benchmark datasets (image domains) and 24.5% on one of the weakly annotated datasets 1 1 Acknowledgements. The authors were supported by Czech Technical University student grant SGS20/171/0HK3/3TJ13, the MEYS VVV project CZ.02.1.01/0.010.0J16 019/0000765 Research Center for Informatics, the Spanish Research project TIN2017-89779-P and the CERCA Programme / Generalitat de Catalunya. |
|
|
Address |
Virtual; January 2021 |
|
|
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 |
ICPR |
|
|
Notes |
DAG; 600.121; 600.129 |
Approved |
no |
|
|
Call Number |
Admin @ si @ JMG2020 |
Serial |
3557 |
|
Permanent link to this record |
|
|
|
|
Author |
Minesh Mathew; Ruben Tito; Dimosthenis Karatzas; R.Manmatha; C.V. Jawahar |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Document Visual Question Answering Challenge 2020 |
Type |
Conference Article |
|
Year |
2020 |
Publication |
33rd IEEE Conference on Computer Vision and Pattern Recognition – Short paper |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
This paper presents results of Document Visual Question Answering Challenge organized as part of “Text and Documents in the Deep Learning Era” workshop, in CVPR 2020. The challenge introduces a new problem – Visual Question Answering on document images. The challenge comprised two tasks. The first task concerns with asking questions on a single document image. On the other hand, the second task is set as a retrieval task where the question is posed over a collection of images. For the task 1 a new dataset is introduced comprising 50,000 questions-answer(s) pairs defined over 12,767 document images. For task 2 another dataset has been created comprising 20 questions over 14,362 document images which share the same document template. |
|
|
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 |
CVPR |
|
|
Notes |
DAG; 600.121 |
Approved |
no |
|
|
Call Number |
Admin @ si @ MTK2020 |
Serial |
3558 |
|
Permanent link to this record |
|
|
|
|
Author |
Ozge Mercanoglu Sincan; Julio C. S. Jacques Junior; Sergio Escalera; Hacer Yalim Keles |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
ChaLearn LAP Large Scale Signer Independent Isolated Sign Language Recognition Challenge: Design, Results and Future Research |
Type |
Conference Article |
|
Year |
2021 |
Publication |
Conference on Computer Vision and Pattern Recognition Workshops |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
3467-3476 |
|
|
Keywords |
|
|
|
Abstract |
The performances of Sign Language Recognition (SLR) systems have improved considerably in recent years. However, several open challenges still need to be solved to allow SLR to be useful in practice. The research in the field is in its infancy in regards to the robustness of the models to a large diversity of signs and signers, and to fairness of the models to performers from different demographics. This work summarises the ChaLearn LAP Large Scale Signer Independent Isolated SLR Challenge, organised at CVPR 2021 with the goal of overcoming some of the aforementioned challenges. We analyse and discuss the challenge design, top winning solutions and suggestions for future research. The challenge attracted 132 participants in the RGB track and 59 in the RGB+Depth track, receiving more than 1.5K submissions in total. Participants were evaluated using a new large-scale multi-modal Turkish Sign Language (AUTSL) dataset, consisting of 226 sign labels and 36,302 isolated sign video samples performed by 43 different signers. Winning teams achieved more than 96% recognition rate, and their approaches benefited from pose/hand/face estimation, transfer learning, external data, fusion/ensemble of modalities and different strategies to model spatio-temporal information. However, methods still fail to distinguish among very similar signs, in particular those sharing similar hand trajectories. |
|
|
Address |
Virtual; June 2021 |
|
|
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 |
HuPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ MJE2021 |
Serial |
3560 |
|
Permanent link to this record |
|
|
|
|
Author |
Marc Masana; Tinne Tuytelaars; Joost Van de Weijer |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Ternary Feature Masks: zero-forgetting for task-incremental learning |
Type |
Conference Article |
|
Year |
2021 |
Publication |
34th IEEE Conference on Computer Vision and Pattern Recognition Workshops |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
3565-3574 |
|
|
Keywords |
|
|
|
Abstract |
We propose an approach without any forgetting to continual learning for the task-aware regime, where at inference the task-label is known. By using ternary masks we can upgrade a model to new tasks, reusing knowledge from previous tasks while not forgetting anything about them. Using masks prevents both catastrophic forgetting and backward transfer. We argue -- and show experimentally -- that avoiding the former largely compensates for the lack of the latter, which is rarely observed in practice. In contrast to earlier works, our masks are applied to the features (activations) of each layer instead of the weights. This considerably reduces the number of mask parameters for each new task; with more than three orders of magnitude for most networks. The encoding of the ternary masks into two bits per feature creates very little overhead to the network, avoiding scalability issues. To allow already learned features to adapt to the current task without changing the behavior of these features for previous tasks, we introduce task-specific feature normalization. Extensive experiments on several finegrained datasets and ImageNet show that our method outperforms current state-of-the-art while reducing memory overhead in comparison to weight-based approaches. |
|
|
Address |
Virtual; June 2021 |
|
|
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; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ MTW2021 |
Serial |
3565 |
|
Permanent link to this record |
|
|
|
|
Author |
Sudeep Katakol; Luis Herranz; Fei Yang; Marta Mrak |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
DANICE: Domain adaptation without forgetting in neural image compression |
Type |
Conference Article |
|
Year |
2021 |
Publication |
Conference on Computer Vision and Pattern Recognition Workshops |
Abbreviated Journal |
|
|
|
Volume ![sorted by Volume (numeric) field, ascending order (up)](img/sort_asc.gif) |
|
Issue |
|
Pages |
1921-1925 |
|
|
Keywords |
|
|
|
Abstract |
Neural image compression (NIC) is a new coding paradigm where coding capabilities are captured by deep models learned from data. This data-driven nature enables new potential functionalities. In this paper, we study the adaptability of codecs to custom domains of interest. We show that NIC codecs are transferable and that they can be adapted with relatively few target domain images. However, naive adaptation interferes with the solution optimized for the original source domain, resulting in forgetting the original coding capabilities in that domain, and may even break the compatibility with previously encoded bitstreams. Addressing these problems, we propose Codec Adaptation without Forgetting (CAwF), a framework that can avoid these problems by adding a small amount of custom parameters, where the source codec remains embedded and unchanged during the adaptation process. Experiments demonstrate its effectiveness and provide useful insights on the characteristics of catastrophic interference in NIC. |
|
|
Address |
Virtual; June 2021 |
|
|
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; 600.120; 600.141; 601.379 |
Approved |
no |
|
|
Call Number |
Admin @ si @ KHY2021 |
Serial |
3568 |
|
Permanent link to this record |