Home | [161–170] << 171 172 173 174 175 176 177 178 179 180 >> [181–190] |
![]() |
Records | |||||
---|---|---|---|---|---|
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 | 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 | Mireia Sole; Joan Blanco; Debora Gil; Oliver Valero; Alvaro Pascual; B. Cardenas; G. Fonseka; E. Anton; Richard Frodsham; Francesca Vidal; Zaida Sarrate | ||||
Title | Chromosomal positioning in spermatogenic cells is influenced by chromosomal factors associated with gene activity, bouquet formation, and meiotic sex-chromosome inactivation | Type | Journal Article | ||
Year | 2021 | Publication | Chromosoma | Abbreviated Journal | |
Volume | 130 | Issue | Pages | 163-175 | |
Keywords | |||||
Abstract | Chromosome territoriality is not random along the cell cycle and it is mainly governed by intrinsic chromosome factors and gene expression patterns. Conversely, very few studies have explored the factors that determine chromosome territoriality and its influencing factors during meiosis. In this study, we analysed chromosome positioning in murine spermatogenic cells using three-dimensionally fluorescence in situ hybridization-based methodology, which allows the analysis of the entire karyotype. The main objective of the study was to decipher chromosome positioning in a radial axis (all analysed germ-cell nuclei) and longitudinal axis (only spermatozoa) and to identify the chromosomal factors that regulate such an arrangement. Results demonstrated that the radial positioning of chromosomes during spermatogenesis was cell-type specific and influenced by chromosomal factors associated to gene activity. Chromosomes with specific features that enhance transcription (high GC content, high gene density and high numbers of predicted expressed genes) were preferentially observed in the inner part of the nucleus in virtually all cell types. Moreover, the position of the sex chromosomes was influenced by their transcriptional status, from the periphery of the nucleus when its activity was repressed (pachytene) to a more internal position when it is partially activated (spermatid). At pachytene, chromosome positioning was also influenced by chromosome size due to the bouquet formation. Longitudinal chromosome positioning in the sperm nucleus was not random either, suggesting the importance of ordered longitudinal positioning for the release and activation of the paternal genome after fertilisation. | ||||
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 @ SBG2021 | Serial | 3592 | ||
Permanent link to this record | |||||
Author | Marta Ligero; Alonso Garcia Ruiz; Cristina Viaplana; Guillermo Villacampa; Maria V Raciti; Jaid Landa; Ignacio Matos; Juan Martin Liberal; Maria Ochoa de Olza; Cinta Hierro; Joaquin Mateo; Macarena Gonzalez; Rafael Morales Barrera; Cristina Suarez; Jordi Rodon; Elena Elez; Irene Braña; Eva Muñoz-Couselo; Ana Oaknin; Roberta Fasani; Paolo Nuciforo; Debora Gil; Carlota Rubio Perez; Joan Seoane; Enriqueta Felip; Manuel Escobar; Josep Tabernero; Joan Carles; Rodrigo Dienstmann; Elena Garralda; Raquel Perez Lopez | ||||
Title | A CT-based radiomics signature is associated with response to immune checkpoint inhibitors in advanced solid tumors | Type | Journal Article | ||
Year | 2021 | Publication | Radiology | Abbreviated Journal | |
Volume | 299 | Issue | 1 | Pages | 109-119 |
Keywords | |||||
Abstract | Background Reliable predictive imaging markers of response to immune checkpoint inhibitors are needed. Purpose To develop and validate a pretreatment CT-based radiomics signature to predict response to immune checkpoint inhibitors in advanced solid tumors. Materials and Methods In this retrospective study, a radiomics signature was developed in patients with advanced solid tumors (including breast, cervix, gastrointestinal) treated with anti-programmed cell death-1 or programmed cell death ligand-1 monotherapy from August 2012 to May 2018 (cohort 1). This was tested in patients with bladder and lung cancer (cohorts 2 and 3). Radiomics variables were extracted from all metastases delineated at pretreatment CT and selected by using an elastic-net model. A regression model combined radiomics and clinical variables with response as the end point. Biologic validation of the radiomics score with RNA profiling of cytotoxic cells (cohort 4) was assessed with Mann-Whitney analysis. Results The radiomics signature was developed in 85 patients (cohort 1: mean age, 58 years ± 13 [standard deviation]; 43 men) and tested on 46 patients (cohort 2: mean age, 70 years ± 12; 37 men) and 47 patients (cohort 3: mean age, 64 years ± 11; 40 men). Biologic validation was performed in a further cohort of 20 patients (cohort 4: mean age, 60 years ± 13; 14 men). The radiomics signature was associated with clinical response to immune checkpoint inhibitors (area under the curve [AUC], 0.70; 95% CI: 0.64, 0.77; P < .001). In cohorts 2 and 3, the AUC was 0.67 (95% CI: 0.58, 0.76) and 0.67 (95% CI: 0.56, 0.77; P < .001), respectively. A radiomics-clinical signature (including baseline albumin level and lymphocyte count) improved on radiomics-only performance (AUC, 0.74 [95% CI: 0.63, 0.84; P < .001]; Akaike information criterion, 107.00 and 109.90, respectively). Conclusion A pretreatment CT-based radiomics signature is associated with response to immune checkpoint inhibitors, likely reflecting the tumor immunophenotype. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Summers in this issue. | ||||
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 @ LGV2021 | Serial | 3593 | ||
Permanent link to this record | |||||
Author | Debora Gil; Oriol Ramos Terrades; Raquel Perez | ||||
Title | Topological Radiomics (TOPiomics): Early Detection of Genetic Abnormalities in Cancer Treatment Evolution | Type | Book Chapter | ||
Year | 2021 | Publication | Extended Abstracts GEOMVAP 2019, Trends in Mathematics 15 | Abbreviated Journal | |
Volume | 15 | Issue | Pages | 89–93 | |
Keywords | |||||
Abstract | Abnormalities in radiomic measures correlate to genomic alterations prone to alter the outcome of personalized anti-cancer treatments. TOPiomics is a new method for the early detection of variations in tumor imaging phenotype from a topological structure in multi-view radiomic spaces. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Springer Nature | 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; DAG; 600.120; 600.145; 600.139 | Approved | no | ||
Call Number | Admin @ si @ GRP2021 | Serial | 3594 | ||
Permanent link to this record | |||||
Author | Trevor Canham; Javier Vazquez; Elise Mathieu; Marcelo Bertalmío | ||||
Title | Matching visual induction effects on screens of different size | Type | Journal Article | ||
Year | 2021 | Publication | Journal of Vision | Abbreviated Journal | JOV |
Volume | 21 | Issue | 6(10) | Pages | 1-22 |
Keywords | |||||
Abstract | In the film industry, the same movie is expected to be watched on displays of vastly different sizes, from cinema screens to mobile phones. But visual induction, the perceptual phenomenon by which the appearance of a scene region is affected by its surroundings, will be different for the same image shown on two displays of different dimensions. This phenomenon presents a practical challenge for the preservation of the artistic intentions of filmmakers, because it can lead to shifts in image appearance between viewing destinations. In this work, we show that a neural field model based on the efficient representation principle is able to predict induction effects and how, by regularizing its associated energy functional, the model is still able to represent induction but is now invertible. From this finding, we propose a method to preprocess an image in a screen–size dependent way so that its perception, in terms of visual induction, may remain constant across displays of different size. The potential of the method is demonstrated through psychophysical experiments on synthetic images and qualitative examples on natural images. | ||||
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 | CIC | Approved | no | ||
Call Number | Admin @ si @ CVM2021 | Serial | 3595 | ||
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 | 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 | Josep Llados; Daniel Lopresti; Seiichi Uchida (eds) | ||||
Title | 16th International Conference, 2021, Proceedings, Part I | Type | Book Whole | ||
Year | 2021 | Publication | Document Analysis and Recognition – ICDAR 2021 | Abbreviated Journal | |
Volume | 12821 | Issue | Pages | ||
Keywords | |||||
Abstract | This four-volume set of LNCS 12821, LNCS 12822, LNCS 12823 and LNCS 12824, constitutes the refereed proceedings of the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, held in Lausanne, Switzerland in September 2021. The 182 full papers were carefully reviewed and selected from 340 submissions, and are presented with 13 competition reports.
The papers are organized into the following topical sections: historical document analysis, document analysis systems, handwriting recognition, scene text detection and recognition, document image processing, natural language processing (NLP) for document understanding, and graphics, diagram and math recognition. |
||||
Address | Lausanne, Switzerland, September 5-10, 2021 | ||||
Corporate Author | Thesis | ||||
Publisher | Springer Cham | Place of Publication | Editor | Josep Llados; Daniel Lopresti; Seiichi Uchida | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
Series Volume | Series Issue | Edition | |||
ISSN ![]() |
ISBN | 978-3-030-86548-1 | Medium | ||
Area | Expedition | Conference | ICDAR | ||
Notes | DAG | Approved | no | ||
Call Number | Admin @ si @ | Serial | 3725 | ||
Permanent link to this record | |||||
Author | Josep Llados; Daniel Lopresti; Seiichi Uchida (eds) | ||||
Title | 16th International Conference, 2021, Proceedings, Part II | Type | Book Whole | ||
Year | 2021 | Publication | Document Analysis and Recognition – ICDAR 2021 | Abbreviated Journal | |
Volume | 12822 | Issue | Pages | ||
Keywords | |||||
Abstract | This four-volume set of LNCS 12821, LNCS 12822, LNCS 12823 and LNCS 12824, constitutes the refereed proceedings of the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, held in Lausanne, Switzerland in September 2021. The 182 full papers were carefully reviewed and selected from 340 submissions, and are presented with 13 competition reports.
The papers are organized into the following topical sections: document analysis for literature search, document summarization and translation, multimedia document analysis, mobile text recognition, document analysis for social good, indexing and retrieval of documents, physical and logical layout analysis, recognition of tables and formulas, and natural language processing (NLP) for document understanding. |
||||
Address | Lausanne, Switzerland, September 5-10, 2021 | ||||
Corporate Author | Thesis | ||||
Publisher | Springer Cham | Place of Publication | Editor | Josep Llados; Daniel Lopresti; Seiichi Uchida | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
Series Volume | Series Issue | Edition | |||
ISSN ![]() |
ISBN | 978-3-030-86330-2 | Medium | ||
Area | Expedition | Conference | ICDAR | ||
Notes | DAG | Approved | no | ||
Call Number | Admin @ si @ | Serial | 3726 | ||
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 | 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 | 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 | 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 | 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 | |||||
Author | Hassan Ahmed Sial | ||||
Title | Estimating Light Effects from a Single Image: Deep Architectures and Ground-Truth Generation | Type | Book Whole | ||
Year | 2021 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | In this thesis, we explore how to estimate the effects of the light interacting with the scene objects from a single image. To achieve this goal, we focus on recovering intrinsic components like reflectance, shading, or light properties such as color and position using deep architectures. The success of these approaches relies on training on large and diversified image datasets. Therefore, we present several contributions on this such as: (a) a data-augmentation technique; (b) a ground-truth for an existing multi-illuminant dataset; (c) a family of synthetic datasets, SID for Surreal Intrinsic Datasets, with diversified backgrounds and coherent light conditions; and (d) a practical pipeline to create hybrid ground-truths to overcome the complexity of acquiring realistic light conditions in a massive way. In parallel with the creation of datasets, we trained different flexible encoder-decoder deep architectures incorporating physical constraints from the image formation models.
In the last part of the thesis, we apply all the previous experience to two different problems. Firstly, we create a large hybrid Doc3DShade dataset with real shading and synthetic reflectance under complex illumination conditions, that is used to train a two-stage architecture that improves the character recognition task in complex lighting conditions of unwrapped documents. Secondly, we tackle the problem of single image scene relighting by extending both, the SID dataset to present stronger shading and shadows effects, and the deep architectures to use intrinsic components to estimate new relit images. |
||||
Address | September 2021 | ||||
Corporate Author | Thesis | Ph.D. thesis | |||
Publisher | IMPRIMA | Place of Publication | Editor | Maria Vanrell;Ramon Baldrich | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN ![]() |
ISBN | 978-84-122714-8-5 | Medium | ||
Area | Expedition | Conference | |||
Notes | CIC; | Approved | no | ||
Call Number | Admin @ si @ Sia2021 | Serial | 3607 | ||
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 | Javad Zolfaghari Bengar | ||||
Title | Reducing Label Effort with Deep Active Learning | Type | Book Whole | ||
Year | 2021 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | Deep convolutional neural networks (CNNs) have achieved superior performance in many visual recognition applications, such as image classification, detection and segmentation. Training deep CNNs requires huge amounts of labeled data, which is expensive and labor intensive to collect. Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected
informative and/or representative samples. In this thesis we study several aspects of active learning including video object detection for autonomous driving systems, image classification on balanced and imbalanced datasets and the incorporation of self-supervised learning in active learning. We briefly describe our approach in each of these areas to reduce the labeling effort. In chapter two we introduce a novel active learning approach for object detection in videos by exploiting temporal coherence. Our criterion is based on the estimated number of errors in terms of false positives and false negatives. Additionally, we introduce a synthetic video dataset, called SYNTHIA-AL, specially designed to evaluate active learning for video object detection in road scenes. Finally, we show that our approach outperforms active learning baselines tested on two outdoor datasets. In the next chapter we address the well-known problem of over confidence in the neural networks. As an alternative to network confidence, we propose a new informativeness-based active learning method that captures the learning dynamics of neural network with a metric called label-dispersion. This metric is low when the network consistently assigns the same label to the sample during the course of training and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results. In chapter four, we tackle the problem of sampling bias in active learning methods on imbalanced datasets. Active learning is generally studied on balanced datasets where an equal amount of images per class is available. However, real-world datasets suffer from severe imbalanced classes, the so called longtail distribution. We argue that this further complicates the active learning process, since the imbalanced data pool can result in suboptimal classifiers. To address this problem in the context of active learning, we propose a general optimization framework that explicitly takes class-balancing into account. Results on three datasets show that the method is general (it can be combined with most existing active learning algorithms) and can be effectively applied to boost the performance of both informative and representative-based active learning methods. In addition, we show that also on balanced datasets our method generally results in a performance gain. Another paradigm to reduce the annotation effort is self-training that learns from a large amount of unlabeled data in an unsupervised way and fine-tunes on few labeled samples. Recent advancements in self-training have achieved very impressive results rivaling supervised learning on some datasets. In the last chapter we focus on whether active learning and self supervised learning can benefit from each other. We study object recognition datasets with several labeling budgets for the evaluations. Our experiments reveal that self-training is remarkably more efficient than active learning at reducing the labeling effort, that for a low labeling budget, active learning offers no benefit to self-training, and finally that the combination of active learning and self-training is fruitful when the labeling budget is high. |
||||
Address | December 2021 | ||||
Corporate Author | Thesis | Ph.D. thesis | |||
Publisher | IMPRIMA | Place of Publication | Editor | Joost Van de Weijer;Bogdan Raducanu | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN ![]() |
ISBN | 978-84-122714-9-2 | Medium | ||
Area | Expedition | Conference | |||
Notes | LAMP; | Approved | no | ||
Call Number | Admin @ si @ Zol2021 | Serial | 3609 | ||
Permanent link to this record |