Home [111–120] << 121 122 123 124 125 126 127 128 129 130 >> [131–140]
List View
 | 
Citations
 | 
Details
   web
Records
Author Marc Masana; Tinne Tuytelaars; Joost Van de Weijer
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 (up) 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
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 (up) 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
 
 
Author Fei Yang; Luis Herranz; Yongmei Cheng; Mikhail Mozerov
Title Slimmable compressive autoencoders for practical neural image compression Type Conference Article
Year 2021 Publication 34th IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal
Volume (up) Issue Pages 4996-5005
Keywords
Abstract Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimized for a single rate, limiting their practical use. Focusing on practical image compression, we propose slimmable compressive autoencoders (SlimCAEs), where rate (R) and distortion (D) are jointly optimized for different capacities. Once trained, encoders and decoders can be executed at different capacities, leading to different rates and complexities. We show that a successful implementation of SlimCAEs requires suitable capacity-specific RD tradeoffs. Our experiments show that SlimCAEs are highly flexible models that provide excellent rate-distortion performance, variable rate, and dynamic adjustment of memory, computational cost and latency, thus addressing the main requirements of practical image compression.
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 CVPR
Notes LAMP; 600.120 Approved no
Call Number Admin @ si @ YHC2021 Serial 3569
Permanent link to this record
 
 
Author Patricia Suarez; Angel Sappa; Boris X. Vintimilla
Title Deep learning-based vegetation index estimation Type Book Chapter
Year 2021 Publication Generative Adversarial Networks for Image-to-Image Translation Abbreviated Journal
Volume (up) Issue Pages 205-234
Keywords
Abstract Chapter 9
Address
Corporate Author Thesis
Publisher Elsevier Place of Publication Editor A.Solanki; A.Nayyar; M.Naved
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; 600.122 Approved no
Call Number Admin @ si @ SSV2021a Serial 3578
Permanent link to this record
 
 
Author Patricia Suarez; Angel Sappa; Boris X. Vintimilla; Riad I. Hammoud
Title Cycle Generative Adversarial Network: Towards A Low-Cost Vegetation Index Estimation Type Conference Article
Year 2021 Publication 28th IEEE International Conference on Image Processing Abbreviated Journal
Volume (up) Issue Pages 19-22
Keywords
Abstract This paper presents a novel unsupervised approach to estimate the Normalized Difference Vegetation Index (NDVI). The NDVI is obtained as the ratio between information from the visible and near infrared spectral bands; in the current work, the NDVI is estimated just from an image of the visible spectrum through a Cyclic Generative Adversarial Network (CyclicGAN). This unsupervised architecture learns to estimate the NDVI index by means of an image translation between the red channel of a given RGB image and the NDVI unpaired index’s image. The translation is obtained by means of a ResNET architecture and a multiple loss function. Experimental results obtained with this unsupervised scheme show the validity of the implemented model. Additionally, comparisons with the state of the art approaches are provided showing improvements with the proposed approach.
Address Anchorage-Alaska; USA; September 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 ICIP
Notes MSIAU; 600.130; 600.122; 601.349 Approved no
Call Number Admin @ si @ SSV2021b Serial 3579
Permanent link to this record
 
 
Author Rafael E. Rivadeneira; Angel Sappa; Boris X. Vintimilla; Sabari Nathan; Priya Kansal; Armin Mehri; Parichehr Behjati Ardakani; A.Dalal; A.Akula; D.Sharma; S.Pandey; B.Kumar; J.Yao; R.Wu; KFeng; N.Li; Y.Zhao; H.Patel; V. Chudasama; K.Pjajapati; A.Sarvaiya; K.Upla; K.Raja; R.Ramachandra; C.Bush; F.Almasri; T.Vandamme; O.Debeir; N.Gutierrez; Q.Nguyen; W.Beksi
Title Thermal Image Super-Resolution Challenge – PBVS 2021 Type Conference Article
Year 2021 Publication Conference on Computer Vision and Pattern Recognition Workshops Abbreviated Journal
Volume (up) Issue Pages 4359-4367
Keywords
Abstract This paper presents results from the second Thermal Image Super-Resolution (TISR) challenge organized in the framework of the Perception Beyond the Visible Spectrum (PBVS) 2021 workshop. For this second edition, the same thermal image dataset considered during the first challenge has been used; only mid-resolution (MR) and high-resolution (HR) sets have been considered. The dataset consists of 951 training images and 50 testing images for each resolution. A set of 20 images for each resolution is kept aside for evaluation. The two evaluation methodologies proposed for the first challenge are also considered in this opportunity. The first evaluation task consists of measuring the PSNR and SSIM between the obtained SR image and the corresponding ground truth (i.e., the HR thermal image downsampled by four). The second evaluation also consists of measuring the PSNR and SSIM, but in this case, considers the x2 SR obtained from the given MR thermal image; this evaluation is performed between the SR image with respect to the semi-registered HR image, which has been acquired with another camera. The results outperformed those from the first challenge, thus showing an improvement in both evaluation metrics.
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 MSIAU; 600.130; 600.122 Approved no
Call Number Admin @ si @ RSV2021 Serial 3581
Permanent link to this record
 
 
Author Armin Mehri; Parichehr Behjati Ardakani; Angel Sappa
Title MPRNet: Multi-Path Residual Network for Lightweight Image Super Resolution Type Conference Article
Year 2021 Publication IEEE Winter Conference on Applications of Computer Vision Abbreviated Journal
Volume (up) Issue Pages 2703-2712
Keywords
Abstract Lightweight super resolution networks have extremely importance for real-world applications. In recent years several SR deep learning approaches with outstanding achievement have been introduced by sacrificing memory and computational cost. To overcome this problem, a novel lightweight super resolution network is proposed, which improves the SOTA performance in lightweight SR and performs roughly similar to computationally expensive networks. Multi-Path Residual Network designs with a set of Residual concatenation Blocks stacked with Adaptive Residual Blocks: ($i$) to adaptively extract informative features and learn more expressive spatial context information; ($ii$) to better leverage multi-level representations before up-sampling stage; and ($iii$) to allow an efficient information and gradient flow within the network. The proposed architecture also contains a new attention mechanism, Two-Fold Attention Module, to maximize the representation ability of the model. Extensive experiments show the superiority of our model against other SOTA SR approaches.
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 WACV
Notes MSIAU; 600.130; 600.122 Approved no
Call Number Admin @ si @ MAS2021b Serial 3582
Permanent link to this record
 
 
Author Armin Mehri; Parichehr Behjati Ardakani; Angel Sappa
Title LiNet: A Lightweight Network for Image Super Resolution Type Conference Article
Year 2021 Publication 25th International Conference on Pattern Recognition Abbreviated Journal
Volume (up) Issue Pages 7196-7202
Keywords
Abstract This paper proposes a new lightweight network, LiNet, that enhancing technical efficiency in lightweight super resolution and operating approximately like very large and costly networks in terms of number of network parameters and operations. The proposed architecture allows the network to learn more abstract properties by avoiding low-level information via multiple links. LiNet introduces a Compact Dense Module, which contains set of inner and outer blocks, to efficiently extract meaningful information, to better leverage multi-level representations before upsampling stage, and to allow an efficient information and gradient flow within the network. Experiments on benchmark datasets show that the proposed LiNet achieves favorable performance against lightweight state-of-the-art methods.
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
Notes MSIAU; 600.130; 600.122 Approved no
Call Number Admin @ si @ MAS2021a Serial 3583
Permanent link to this record
 
 
Author Albin Soutif; Marc Masana; Joost Van de Weijer; Bartlomiej Twardowski
Title On the importance of cross-task features for class-incremental learning Type Conference Article
Year 2021 Publication Theory and Foundation of continual learning workshop of ICML Abbreviated Journal
Volume (up) Issue Pages
Keywords
Abstract In class-incremental learning, an agent with limited resources needs to learn a sequence of classification tasks, forming an ever growing classification problem, with the constraint of not being able to access data from previous tasks. The main difference with task-incremental learning, where a task-ID is available at inference time, is that the learner also needs to perform crosstask discrimination, i.e. distinguish between classes that have not been seen together. Approaches to tackle this problem are numerous and mostly make use of an external memory (buffer) of non-negligible size. In this paper, we ablate the learning of crosstask features and study its influence on the performance of basic replay strategies used for class-IL. We also define a new forgetting measure for class-incremental learning, and see that forgetting is not the principal cause of low performance. Our experimental results show that future algorithms for class-incremental learning should not only prevent forgetting, but also aim to improve the quality of the cross-task features. This is especially important when the number of classes per task is small.
Address Virtual; July 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 ICMLW
Notes LAMP Approved no
Call Number Admin @ si @ SMW2021 Serial 3588
Permanent link to this record
 
 
Author Sonia Baeza; R.Domingo; M.Salcedo; G.Moragas; J.Deportos; I.Garcia Olive; Carles Sanchez; Debora Gil; Antoni Rosell
Title Artificial Intelligence to Optimize Pulmonary Embolism Diagnosis During Covid-19 Pandemic by Perfusion SPECT/CT, a Pilot Study Type Journal Article
Year 2021 Publication American Journal of Respiratory and Critical Care Medicine Abbreviated Journal
Volume (up) Issue Pages
Keywords
Abstract
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 IAM; 600.145 Approved no
Call Number Admin @ si @ BDS2021 Serial 3591
Permanent link to this record
 
 
Author Graham D. Finlayson; Javier Vazquez; Fufu Fang
Title The Discrete Cosine Maximum Ignorance Assumption Type Conference Article
Year 2021 Publication 29th Color and Imaging Conference Abbreviated Journal
Volume (up) Issue Pages 13-18
Keywords
Abstract the performance of colour correction algorithms are dependent on the reflectance sets used. Sometimes, when the testing reflectance set is changed the ranking of colour correction algorithms also changes. To remove dependence on dataset we can
make assumptions about the set of all possible reflectances. In the Maximum Ignorance with Positivity (MIP) assumption we assume that all reflectances with per wavelength values between 0 and 1 are equally likely. A weakness in the MIP is that it fails to take into account the correlation of reflectance functions between
wavelengths (many of the assumed reflectances are, in reality, not possible).
In this paper, we take the view that the maximum ignorance assumption has merit but, hitherto it has been calculated with respect to the wrong coordinate basis. Here, we propose the Discrete Cosine Maximum Ignorance assumption (DCMI), where
all reflectances that have coordinates between max and min bounds in the Discrete Cosine Basis coordinate system are equally likely.
Here, the correlation between wavelengths is encoded and this results in the set of all plausible reflectances ’looking like’ typical reflectances that occur in nature. This said the DCMI model is also a superset of all measured reflectance sets.
Experiments show that, in colour correction, adopting the DCMI results in similar colour correction performance as using a particular reflectance set.
Address Virtual; November 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 CIC
Notes CIC Approved no
Call Number FVF2021 Serial 3596
Permanent link to this record
 
 
Author Razieh Rastgoo; Kourosh Kiani; Sergio Escalera; Mohammad Sabokrou
Title Sign Language Production: A Review Type Conference Article
Year 2021 Publication Conference on Computer Vision and Pattern Recognition Workshops Abbreviated Journal
Volume (up) Issue Pages 3472-3481
Keywords
Abstract Sign Language is the dominant yet non-primary form of communication language used in the deaf and hearing-impaired community. To make an easy and mutual communication between the hearing-impaired and the hearing communities, building a robust system capable of translating the spoken language into sign language and vice versa is fundamental. To this end, sign language recognition and production are two necessary parts for making such a two-way system. Sign language recognition and production need to cope with some critical challenges. In this survey, we review recent advances in Sign Language Production (SLP) and related areas using deep learning. This survey aims to briefly summarize recent achievements in SLP, discussing their advantages, limitations, and future directions of research.
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 @ RKE2021b Serial 3603
Permanent link to this record
 
 
Author Yaxing Wang; Hector Laria Mantecon; Joost Van de Weijer; Laura Lopez-Fuentes; Bogdan Raducanu
Title TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets Type Conference Article
Year 2021 Publication 19th IEEE International Conference on Computer Vision Abbreviated Journal
Volume (up) Issue Pages 13990-13999
Keywords
Abstract Image-to-image (I2I) translation has matured in recent years and is able to generate high-quality realistic images. However, despite current success, it still faces important challenges when applied to small domains. Existing methods use transfer learning for I2I translation, but they still require the learning of millions of parameters from scratch. This drawback severely limits its application on small domains. In this paper, we propose a new transfer learning for I2I translation (TransferI2I). We decouple our learning process into the image generation step and the I2I translation step. In the first step we propose two novel techniques: source-target initialization and self-initialization of the adaptor layer. The former finetunes the pretrained generative model (e.g., StyleGAN) on source and target data. The latter allows to initialize all non-pretrained network parameters without the need of any data. These techniques provide a better initialization for the I2I translation step. In addition, we introduce an auxiliary GAN that further facilitates the training of deep I2I systems even from small datasets. In extensive experiments on three datasets, (Animal faces, Birds, and Foods), we show that we outperform existing methods and that mFID improves on several datasets with over 25 points.
Address Virtual; October 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 ICCV
Notes LAMP; 600.147; 602.200; 600.120 Approved no
Call Number Admin @ si @ WLW2021 Serial 3604
Permanent link to this record
 
 
Author Shiqi Yang; Yaxing Wang; Joost Van de Weijer; Luis Herranz; Shangling Jui
Title Generalized Source-free Domain Adaptation Type Conference Article
Year 2021 Publication 19th IEEE International Conference on Computer Vision Abbreviated Journal
Volume (up) Issue Pages 8958-8967
Keywords
Abstract Domain adaptation (DA) aims to transfer the knowledge learned from a source domain to an unlabeled target domain. Some recent works tackle source-free domain adaptation (SFDA) where only a source pre-trained model is available for adaptation to the target domain. However, those methods do not consider keeping source performance which is of high practical value in real world applications. In this paper, we propose a new domain adaptation paradigm called Generalized Source-free Domain Adaptation (G-SFDA), where the learned model needs to perform well on both the target and source domains, with only access to current unlabeled target data during adaptation. First, we propose local structure clustering (LSC), aiming to cluster the target features with its semantically similar neighbors, which successfully adapts the model to the target domain in the absence of source data. Second, we propose sparse domain attention (SDA), it produces a binary domain specific attention to activate different feature channels for different domains, meanwhile the domain attention will be utilized to regularize the gradient during adaptation to keep source information. In the experiments, for target performance our method is on par with or better than existing DA and SFDA methods, specifically it achieves state-of-the-art performance (85.4%) on VisDA, and our method works well for all domains after adapting to single or multiple target domains.
Address Virtual; October 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
Notes LAMP; 600.120; 600.147 Approved no
Call Number Admin @ si @ YWW2021 Serial 3605
Permanent link to this record
 
 
Author Hugo Bertiche; Meysam Madadi; Emilio Tylson; Sergio Escalera
Title DeePSD: Automatic Deep Skinning And Pose Space Deformation For 3D Garment Animation Type Conference Article
Year 2021 Publication 19th IEEE International Conference on Computer Vision Abbreviated Journal
Volume (up) Issue Pages 5471-5480
Keywords
Abstract We present a novel solution to the garment animation problem through deep learning. Our contribution allows animating any template outfit with arbitrary topology and geometric complexity. Recent works develop models for garment edition, resizing and animation at the same time by leveraging the support body model (encoding garments as body homotopies). This leads to complex engineering solutions that suffer from scalability, applicability and compatibility. By limiting our scope to garment animation only, we are able to propose a simple model that can animate any outfit, independently of its topology, vertex order or connectivity. Our proposed architecture maps outfits to animated 3D models into the standard format for 3D animation (blend weights and blend shapes matrices), automatically providing of compatibility with any graphics engine. We also propose a methodology to complement supervised learning with an unsupervised physically based learning that implicitly solves collisions and enhances cloth quality.
Address Virtual; October 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 ICCV
Notes HUPBA; no menciona Approved no
Call Number Admin @ si @ BMT2021 Serial 3606
Permanent link to this record