| Home | << 1 2 3 4 5 6 7 8 9 >> |
|
| Records | |||||
|---|---|---|---|---|---|
| Author | Ruben Tito; Dimosthenis Karatzas; Ernest Valveny | ||||
| Title | Document Collection Visual Question Answering | Type | Conference Article | ||
| Year | 2021 | Publication | 16th International Conference on Document Analysis and Recognition | Abbreviated Journal | |
| Volume | 12822 | Issue | Pages | 778-792 | |
| Keywords | Document collection; Visual Question Answering | ||||
| Abstract | Current tasks and methods in Document Understanding aims to process documents as single elements. However, documents are usually organized in collections (historical records, purchase invoices), that provide context useful for their interpretation. To address this problem, we introduce Document Collection Visual Question Answering (DocCVQA) a new dataset and related task, where questions are posed over a whole collection of document images and the goal is not only to provide the answer to the given question, but also to retrieve the set of documents that contain the information needed to infer the answer. Along with the dataset we propose a new evaluation metric and baselines which provide further insights to the new dataset and task. | ||||
| Address | |||||
| 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 | ICDAR | ||
| Notes | DAG; 600.121 | Approved | no | ||
Call Number  |
Admin @ si @ TKV2021 | Serial | 3622 | ||
| Permanent link to this record | |||||
| Author | Ruben Tito; Minesh Mathew; C.V. Jawahar; Ernest Valveny; Dimosthenis Karatzas | ||||
| Title | ICDAR 2021 Competition on Document Visual Question Answering | Type | Conference Article | ||
| Year | 2021 | Publication | 16th International Conference on Document Analysis and Recognition | Abbreviated Journal | |
| Volume | Issue | Pages | 635-649 | ||
| Keywords | |||||
| Abstract | In this report we present results of the ICDAR 2021 edition of the Document Visual Question Challenges. This edition complements the previous tasks on Single Document VQA and Document Collection VQA with a newly introduced on Infographics VQA. Infographics VQA is based on a new dataset of more than 5, 000 infographics images and 30, 000 question-answer pairs. The winner methods have scored 0.6120 ANLS in Infographics VQA task, 0.7743 ANLSL in Document Collection VQA task and 0.8705 ANLS in Single Document VQA. We present a summary of the datasets used for each task, description of each of the submitted methods and the results and analysis of their performance. A summary of the progress made on Single Document VQA since the first edition of the DocVQA 2020 challenge is also presented. | ||||
| Address | VIRTUAL; Lausanne; Suissa; 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 | ICDAR | ||
| Notes | DAG; 600.121 | Approved | no | ||
| Call Number |
Admin @ si @ TMJ2021 | Serial | 3624 | ||
| Permanent link to this record | |||||
| Author | Pau Torras; Mohamed Ali Souibgui; Jialuo Chen; Alicia Fornes | ||||
| Title | A Transcription Is All You Need: Learning to Align through Attention | Type | Conference Article | ||
| Year | 2021 | Publication | 14th IAPR International Workshop on Graphics Recognition | Abbreviated Journal | |
| Volume | 12916 | Issue | Pages | 141–146 | |
| Keywords | |||||
| Abstract | Historical ciphered manuscripts are a type of document where graphical symbols are used to encrypt their content instead of regular text. Nowadays, expert transcriptions can be found in libraries alongside the corresponding manuscript images. However, those transcriptions are not aligned, so these are barely usable for training deep learning-based recognition methods. To solve this issue, we propose a method to align each symbol in the transcript of an image with its visual representation by using an attention-based Sequence to Sequence (Seq2Seq) model. The core idea is that, by learning to recognise symbols sequence within a cipher line image, the model also identifies their position implicitly through an attention mechanism. Thus, the resulting symbol segmentation can be later used for training algorithms. The experimental evaluation shows that this method is promising, especially taking into account the small size of the cipher dataset. | ||||
| Address | Virtual; September 2021 | ||||
| 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 | GREC | ||
| Notes | DAG; 602.230; 600.140; 600.121 | Approved | no | ||
| Call Number |
Admin @ si @ TSC2021 | Serial | 3619 | ||
| Permanent link to this record | |||||
| Author | Michael Teutsch; Angel Sappa; Riad I. Hammoud | ||||
| Title | Computer Vision in the Infrared Spectrum: Challenges and Approaches | Type | Book Whole | ||
| Year | 2021 | Publication | Synthesis Lectures on Computer Vision | Abbreviated Journal | |
| Volume | 10 | Issue | 2 | Pages | 1-138 |
| Keywords | |||||
| Abstract | Human visual perception is limited to the visual-optical spectrum. Machine vision is not. Cameras sensitive to the different infrared spectra can enhance the abilities of autonomous systems and visually perceive the environment in a holistic way. Relevant scene content can be made visible especially in situations, where sensors of other modalities face issues like a visual-optical camera that needs a source of illumination. As a consequence, not only human mistakes can be avoided by increasing the level of automation, but also machine-induced errors can be reduced that, for example, could make a self-driving car crash into a pedestrian under difficult illumination conditions. Furthermore, multi-spectral sensor systems with infrared imagery as one modality are a rich source of information and can provably increase the robustness of many autonomous systems. Applications that can benefit from utilizing infrared imagery range from robotics to automotive and from biometrics to surveillance. In this book, we provide a brief yet concise introduction to the current state-of-the-art of computer vision and machine learning in the infrared spectrum. Based on various popular computer vision tasks such as image enhancement, object detection, or object tracking, we first motivate each task starting from established literature in the visual-optical spectrum. Then, we discuss the differences between processing images and videos in the visual-optical spectrum and the various infrared spectra. An overview of the current literature is provided together with an outlook for each task. Furthermore, available and annotated public datasets and common evaluation methods and metrics are presented. In a separate chapter, popular applications that can greatly benefit from the use of infrared imagery as a data source are presented and discussed. Among them are automatic target recognition, video surveillance, or biometrics including face recognition. Finally, we conclude with recommendations for well-fitting sensor setups and data processing algorithms for certain computer vision tasks. We address this book to prospective researchers and engineers new to the field but also to anyone who wants to get introduced to the challenges and the approaches of computer vision using infrared images or videos. Readers will be able to start their work directly after reading the book supported by a highly comprehensive backlog of recent and relevant literature as well as related infrared datasets including existing evaluation frameworks. Together with consistently decreasing costs for infrared cameras, new fields of application appear and make computer vision in the infrared spectrum a great opportunity to face nowadays scientific and engineering challenges. | ||||
| 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 | 978-1636392431 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | MSIAU | Approved | no | ||
| Call Number |
Admin @ si @ TSH2021 | Serial | 3666 | ||
| Permanent link to this record | |||||
| Author | Bartlomiej Twardowski; Pawel Zawistowski; Szymon Zaborowski | ||||
| Title | Metric Learning for Session-Based Recommendations | Type | Conference Article | ||
| Year | 2021 | Publication | 43rd edition of the annual BCS-IRSG European Conference on Information Retrieval | Abbreviated Journal | |
| Volume | 12656 | Issue | Pages | 650-665 | |
| Keywords | Session-based recommendations; Deep metric learning; Learning to rank | ||||
| Abstract | Session-based recommenders, used for making predictions out of users’ uninterrupted sequences of actions, are attractive for many applications. Here, for this task we propose using metric learning, where a common embedding space for sessions and items is created, and distance measures dissimilarity between the provided sequence of users’ events and the next action. We discuss and compare metric learning approaches to commonly used learning-to-rank methods, where some synergies exist. We propose a simple architecture for problem analysis and demonstrate that neither extensively big nor deep architectures are necessary in order to outperform existing methods. The experimental results against strong baselines on four datasets are provided with an ablation study. | ||||
| Address | Virtual; March 2021 | ||||
| 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 | ECIR | ||
| Notes | LAMP; 600.120 | Approved | no | ||
| Call Number |
Admin @ si @ TZZ2021 | Serial | 3586 | ||
| Permanent link to this record | |||||
| Author | Diego Velazquez; Josep M. Gonfaus; Pau Rodriguez; Xavier Roca; Seiichi Ozawa; Jordi Gonzalez | ||||
| Title | Logo Detection With No Priors | Type | Journal Article | ||
| Year | 2021 | Publication | IEEE Access | Abbreviated Journal | ACCESS |
| Volume | 9 | Issue | Pages | 106998-107011 | |
| Keywords | |||||
| Abstract | In recent years, top referred methods on object detection like R-CNN have implemented this task as a combination of proposal region generation and supervised classification on the proposed bounding boxes. Although this pipeline has achieved state-of-the-art results in multiple datasets, it has inherent limitations that make object detection a very complex and inefficient task in computational terms. Instead of considering this standard strategy, in this paper we enhance Detection Transformers (DETR) which tackles object detection as a set-prediction problem directly in an end-to-end fully differentiable pipeline without requiring priors. In particular, we incorporate Feature Pyramids (FP) to the DETR architecture and demonstrate the effectiveness of the resulting DETR-FP approach on improving logo detection results thanks to the improved detection of small logos. So, without requiring any domain specific prior to be fed to the model, DETR-FP obtains competitive results on the OpenLogo and MS-COCO datasets offering a relative improvement of up to 30%, when compared to a Faster R-CNN baseline which strongly depends on hand-designed priors. | ||||
| 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 | Approved | no | ||
| Call Number |
Admin @ si @ VGR2021 | Serial | 3664 | ||
| Permanent link to this record | |||||
| Author | Gabriel Villalonga | ||||
| Title | Leveraging Synthetic Data to Create Autonomous Driving Perception Systems | Type | Book Whole | ||
| Year | 2021 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Manually annotating images to develop vision models has been a major bottleneck
since computer vision and machine learning started to walk together. This has been more evident since computer vision falls on the shoulders of data-hungry deep learning techniques. When addressing on-board perception for autonomous driving, the curse of data annotation is exacerbated due to the use of additional sensors such as LiDAR. Therefore, any approach aiming at reducing such a timeconsuming and costly work is of high interest for addressing autonomous driving and, in fact, for any application requiring some sort of artificial perception. In the last decade, it has been shown that leveraging from synthetic data is a paradigm worth to pursue in order to minimizing manual data annotation. The reason is that the automatic process of generating synthetic data can also produce different types of associated annotations (e.g. object bounding boxes for synthetic images and LiDAR pointclouds, pixel/point-wise semantic information, etc.). Directly using synthetic data for training deep perception models may not be the definitive solution in all circumstances since it can appear a synth-to-real domain shift. In this context, this work focuses on leveraging synthetic data to alleviate manual annotation for three perception tasks related to driving assistance and autonomous driving. In all cases, we assume the use of deep convolutional neural networks (CNNs) to develop our perception models. The first task addresses traffic sign recognition (TSR), a kind of multi-class classification problem. We assume that the number of sign classes to be recognized must be suddenly increased without having annotated samples to perform the corresponding TSR CNN re-training. We show that leveraging synthetic samples of such new classes and transforming them by a generative adversarial network (GAN) trained on the known classes (i.e. without using samples from the new classes), it is possible to re-train the TSR CNN to properly classify all the signs for a ∼ 1/4 ratio of new/known sign classes. The second task addresses on-board 2D object detection, focusing on vehicles and pedestrians. In this case, we assume that we receive a set of images without the annotations required to train an object detector, i.e. without object bounding boxes. Therefore, our goal is to self-annotate these images so that they can later be used to train the desired object detector. In order to reach this goal, we leverage from synthetic data and propose a semi-supervised learning approach based on the co-training idea. In fact, we use a GAN to reduce the synthto-real domain shift before applying co-training. Our quantitative results show that co-training and GAN-based image-to-image translation complement each other up to allow the training of object detectors without manual annotation, and still almost reaching the upper-bound performances of the detectors trained from human annotations. While in previous tasks we focus on vision-based perception, the third task we address focuses on LiDAR pointclouds. Our initial goal was to develop a 3D object detector trained on synthetic LiDAR-style pointclouds. While for images we may expect synth/real-to-real domain shift due to differences in their appearance (e.g. when source and target images come from different camera sensors), we did not expect so for LiDAR pointclouds since these active sensors factor out appearance and provide sampled shapes. However, in practice, we have seen that it can be domain shift even among real-world LiDAR pointclouds. Factors such as the sampling parameters of the LiDARs, the sensor suite configuration onboard the ego-vehicle, and the human annotation of 3D bounding boxes, do induce a domain shift. We show it through comprehensive experiments with different publicly available datasets and 3D detectors. This redirected our goal towards the design of a GAN for pointcloud-to-pointcloud translation, a relatively unexplored topic. Finally, it is worth to mention that all the synthetic datasets used for these three tasks, have been designed and generated in the context of this PhD work and will be publicly released. Overall, we think this PhD presents several steps forward to encourage leveraging synthetic data for developing deep perception models in the field of driving assistance and autonomous driving. |
||||
| Address | February 2021 | ||||
| Corporate Author | Thesis | Ph.D. thesis | |||
| Publisher | Ediciones Graficas Rey | Place of Publication | Editor | Antonio Lopez;German Ros | |
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 978-84-122714-2-3 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | ADAS; 600.118 | Approved | no | ||
| Call Number |
Admin @ si @ Vil2021 | Serial | 3599 | ||
| Permanent link to this record | |||||
| Author | Henry Velesaca; Patricia Suarez; Dario Carpio; Angel Sappa | ||||
| Title | Synthesized Image Datasets: Towards an Annotation-Free Instance Segmentation Strategy | Type | Conference Article | ||
| Year | 2021 | Publication | 16th International Symposium on Visual Computing | Abbreviated Journal | |
| Volume | 13017 | Issue | Pages | 131–143 | |
| Keywords | |||||
| Abstract | This paper presents a complete pipeline to perform deep learning-based instance segmentation of different types of grains (e.g., corn, sunflower, soybeans, lentils, chickpeas, mote, and beans). The proposed approach consists of using synthesized image datasets for the training process, which are easily generated according to the category of the instance to be segmented. The synthesized imaging process allows generating a large set of well-annotated grain samples with high variability—as large and high as the user requires. Instance segmentation is performed through a popular deep learning based approach, the Mask R-CNN architecture, but any learning-based instance segmentation approach can be considered. Results obtained by the proposed pipeline show that the strategy of using synthesized image datasets for training instance segmentation helps to avoid the time-consuming image annotation stage, as well as to achieve higher intersection over union and average precision performances. Results obtained with different varieties of grains are shown, as well as comparisons with manually annotated images, showing both the simplicity of the process and the improvements in the performance. | ||||
| Address | Virtual; October 2021 | ||||
| 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 | ISVC | ||
| Notes | MSIAU | Approved | no | ||
| Call Number |
Admin @ si @ VSC2021 | Serial | 3667 | ||
| Permanent link to this record | |||||
| Author | Henry Velesaca; Patricia Suarez; Raul Mira; Angel Sappa | ||||
| Title | Computer Vision based Food Grain Classification: a Comprehensive Survey | Type | Journal Article | ||
| Year | 2021 | Publication | Computers and Electronics in Agriculture | Abbreviated Journal | CEA |
| Volume | 187 | Issue | Pages | 106287 | |
| Keywords | |||||
| Abstract | This manuscript presents a comprehensive survey on recent computer vision based food grain classification techniques. It includes state-of-the-art approaches intended for different grain varieties. The approaches proposed in the literature are analyzed according to the processing stages considered in the classification pipeline, making it easier to identify common techniques and comparisons. Additionally, the type of images considered by each approach (i.e., images from the: visible, infrared, multispectral, hyperspectral bands) together with the strategy used to generate ground truth data (i.e., real and synthetic images) are reviewed. Finally, conclusions highlighting future needs and challenges are presented. | ||||
| 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 | MSIAU; 600.130; 600.122 | Approved | no | ||
| Call Number |
Admin @ si @ VSM2021 | Serial | 3576 | ||
| Permanent link to this record | |||||
| Author | Yaxing Wang; Abel Gonzalez-Garcia; Luis Herranz; Joost Van de Weijer | ||||
| Title | Controlling biases and diversity in diverse image-to-image translation | Type | Journal Article | ||
| Year | 2021 | Publication | Computer Vision and Image Understanding | Abbreviated Journal | CVIU |
| Volume | 202 | Issue | Pages | 103082 | |
| Keywords | |||||
| Abstract | JCR 2019 Q2, IF=3.121
The task of unpaired image-to-image translation is highly challenging due to the lack of explicit cross-domain pairs of instances. We consider here diverse image translation (DIT), an even more challenging setting in which an image can have multiple plausible translations. This is normally achieved by explicitly disentangling content and style in the latent representation and sampling different styles codes while maintaining the image content. Despite the success of current DIT models, they are prone to suffer from bias. In this paper, we study the problem of bias in image-to-image translation. Biased datasets may add undesired changes (e.g. change gender or race in face images) to the output translations as a consequence of the particular underlying visual distribution in the target domain. In order to alleviate the effects of this problem we propose the use of semantic constraints that enforce the preservation of desired image properties. Our proposed model is a step towards unbiased diverse image-to-image translation (UDIT), and results in less unwanted changes in the translated images while still performing the wanted transformation. Experiments on several heavily biased datasets show the effectiveness of the proposed techniques in different domains such as faces, objects, and scenes. |
||||
| 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; 600.141; 600.109; 600.147 | Approved | no | ||
| Call Number |
Admin @ si @ WGH2021 | Serial | 3464 | ||
| Permanent link to this record | |||||
| Author | Kai Wang; Luis Herranz; Joost Van de Weijer | ||||
| Title | Continual learning in cross-modal retrieval | Type | Conference Article | ||
| Year | 2021 | Publication | 2nd CLVISION workshop | Abbreviated Journal | |
| Volume | 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 | 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 | 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 | Kai Wang; Joost Van de Weijer; Luis Herranz | ||||
| Title | ACAE-REMIND for online continual learning with compressed feature replay | Type | Journal Article | ||
| Year | 2021 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
| Volume | 150 | Issue | Pages | 122-129 | |
| Keywords | online continual learning; autoencoders; vector quantization | ||||
| Abstract | Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior results than image replay, while requiring less memory. Quantized exemplars can further reduce the memory usage. However, a drawback of these methods is that they use a fixed (or very intransigent) backbone network. This significantly limits the learning of representations that can discriminate between all tasks. To address this problem, we propose an auxiliary classifier auto-encoder (ACAE) module for feature replay at intermediate layers with high compression rates. The reduced memory footprint per image allows us to save more exemplars for replay. In our experiments, we conduct task-agnostic evaluation under online continual learning setting and get state-of-the-art performance on ImageNet-Subset, CIFAR100 and CIFAR10 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 | LAMP; 600.147; 601.379; 600.120; 600.141 | Approved | no | ||
| Call Number |
Admin @ si @ WWH2021 | Serial | 3575 | ||
| Permanent link to this record | |||||
| Author | Fei Yang | ||||
| Title | Towards Practical Neural Image Compression | Type | Book Whole | ||
| Year | 2021 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Images and videos are pervasive in our life and communication. With advances in smart and portable devices, high capacity communication networks and high definition cinema, image and video compression are more relevant than ever. Traditional block-based linear transform codecs such as JPEG, H.264/AVC or the recent H.266/VVC are carefully designed to meet not only the rate-distortion criteria, but also the practical requirements of applications.
Recently, a new paradigm based on deep neural networks (i.e., neural image/video compression) has become increasingly popular due to its ability to learn powerful nonlinear transforms and other coding tools directly from data instead of being crafted by humans, as was usual in previous coding formats. While achieving excellent rate-distortion performance, these approaches are still limited mostly to research environments due to heavy models and other practical limitations, such as being limited to function on a particular rate and due to high memory and computational cost. In this thesis, we study these practical limitations, and designing more practical neural image compression approaches. After analyzing the differences between traditional and neural image compression, our first contribution is the modulated autoencoder (MAE), a framework that includes a mechanism to provide multiple rate-distortion options within a single model with comparable performance to independent models. In a second contribution, we propose the slimmable compressive autoencoder (SlimCAE), which in addition to variable rate, can optimize the complexity of the model and thus reduce significantly the memory and computational burden. Modern generative models can learn custom image transformation directly from suitable datasets following encoder-decoder architectures, task known as image-to-image (I2I) translation. Building on our previous work, we study the problem of distributed I2I translation, where the latent representation is transmitted through a binary channel and decoded in a remote receiving side. We also propose a variant that can perform both translation and the usual autoencoding functionality. Finally, we also consider neural video compression, where the autoencoder is typically augmented with temporal prediction via motion compensation. One of the main bottlenecks of that framework is the optical flow module that estimates the displacement to predict the next frame. Focusing on this module, we propose a method that improves the accuracy of the optical flow estimation and a simplified variant that reduces the computational cost. Key words: neural image compression, neural video compression, optical flow, practical neural image compression, compressive autoencoders, image-to-image translation, deep learning. |
||||
| Address | December 2021 | ||||
| Corporate Author | Thesis | Ph.D. thesis | |||
| Publisher | IMPRIMA | Place of Publication | Editor | Luis Herranz;Mikhail Mozerov;Yongmei Cheng | |
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 978-84-122714-7-8 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | LAMP | Approved | no | ||
| Call Number |
Admin @ si @ Yan2021 | Serial | 3608 | ||
| 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 | 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 | |||||