Publicacions CVC -- Query Results

	Publicacions CVC Home \| Show All \| Simple Search \| Advanced Search \| Add Record \| Import	Login Quick Search: Field: contains: ...
	106–120 of 140 records found matching your query (RSS \| history):

Search & Display Options

Select All Deselect All

<< 1 2 3 4 5 6 7 8 9 10 >>

List View

Citations

Details

	Records
	Author	Mohamed Ali Souibgui
	Title	Document Image Enhancement and Recognition in Low Resource Scenarios: Application to Ciphers and Handwritten Text			Type	Book Whole
	Year	2022	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	In this thesis, we propose different contributions with the goal of enhancing and recognizing historical handwritten document images, especially the ones with rare scripts, such as cipher documents. In the first part, some effective end-to-end models for Document Image Enhancement (DIE) using deep learning models were presented. First, Generative Adversarial Networks (cGAN) for different tasks (document clean-up, binarization, deblurring, and watermark removal) were explored. Next, we further improve the results by recovering the degraded document images into a clean and readable form by integrating a text recognizer into the cGAN model to promote the generated document image to be more readable. Afterward, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion. The second part of the thesis addresses Handwritten Text Recognition (HTR) in low resource scenarios, i.e. when only few labeled training data is available. We propose novel methods for recognizing ciphers with rare scripts. First, a few-shot object detection based method was proposed. Then, we incorporate a progressive learning strategy that automatically assignspseudo-labels to a set of unlabeled data to reduce the human labor of annotating few pages while maintaining the good performance of the model. Secondly, a data generation technique based on Bayesian Program Learning (BPL) is proposed to overcome the lack of data in such rare scripts. Thirdly, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE). This latter self-supervised model is designed to tackle two tasks, text recognition and document image enhancement. The proposed model does not exhibit limitations of previous state-of-the-art methods based on contrastive losses, while at the same time, it requires substantially fewer data samples to converge. In the third part of the thesis, we analyze, from the user perspective, the usage of HTR systems in low resource scenarios. This contrasts with the usual research on HTR, which often focuses on technical aspects only and rarely devotes efforts on implementing software tools for scholars in Humanities.
	Address
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	IMPRIMA	Place of Publication		Editor	Alicia Fornes;Yousri Kessentini
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-124793-8-6	Medium
	Area		Expedition		Conference
	Notes	DAG			Approved	no
	Call Number	Admin @ si @ Sou2022			Serial	3757
Permanent link to this record



	Author	Xavier Soria; Gonzalo Pomboza-Junez; Angel Sappa
	Title	LDC: Lightweight Dense CNN for Edge Detection			Type	Journal Article
	Year	2022	Publication	IEEE Access	Abbreviated Journal	ACCESS
	Volume	10	Issue		Pages	68281-68290
	Keywords
	Abstract	This paper presents a Lightweight Dense Convolutional (LDC) neural network for edge detection. The proposed model is an adaptation of two state-of-the-art approaches, but it requires less than 4% of parameters in comparison with these approaches. The proposed architecture generates thin edge maps and reaches the highest score (i.e., ODS) when compared with lightweight models (models with less than 1 million parameters), and reaches a similar performance when compare with heavy architectures (models with about 35 million parameters). Both quantitative and qualitative results and comparisons with state-of-the-art models, using different edge detection datasets, are provided. The proposed LDC does not use pre-trained weights and requires straightforward hyper-parameter settings. The source code is released at https://github.com/xavysp/LDC
	Address	27 June 2022
	Corporate Author				Thesis
	Publisher	IEEE	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	MSIAU; MACO; 600.160; 600.167			Approved	no
	Call Number	Admin @ si @ SPS2022			Serial	3751
Permanent link to this record



	Author	Angel Sappa; Patricia Suarez; Henry Velesaca; Dario Carpio
	Title	Domain Adaptation in Image Dehazing: Exploring the Usage of Images from Virtual Scenarios			Type	Conference Article
	Year	2022	Publication	16th International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing	Abbreviated Journal
	Volume		Issue		Pages	85-92
	Keywords	Domain adaptation; Synthetic hazed dataset; Dehazing
	Abstract	This work presents a novel domain adaptation strategy for deep learning-based approaches to solve the image dehazing problem. Firstly, a large set of synthetic images is generated by using a realistic 3D graphic simulator; these synthetic images contain different densities of haze, which are used for training the model that is later adapted to any real scenario. The adaptation process requires just a few images to fine-tune the model parameters. The proposed strategy allows overcoming the limitation of training a given model with few images. In other words, the proposed strategy implements the adaptation of a haze removal model trained with synthetic images to real scenarios. It should be noticed that it is quite difficult, if not impossible, to have large sets of pairs of real-world images (with and without haze) to train in a supervised way dehazing algorithms. Experimental results are provided showing the validity of the proposed domain adaptation strategy.
	Address	Lisboa; Portugal; July 2022
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference	CGVCVIP
	Notes	MSIAU; no proj			Approved	no
	Call Number	Admin @ si @ SSV2022			Serial	3804
Permanent link to this record



	Author	Yasuko Sugito; Javier Vazquez; Trevor Canham; Marcelo Bertalmio
	Title	Image quality evaluation in professional HDR/WCG production questions the need for HDR metrics			Type	Journal Article
	Year	2022	Publication	IEEE Transactions on Image Processing	Abbreviated Journal	TIP
	Volume	31	Issue		Pages	5163 - 5177
	Keywords	Measurement; Image color analysis; Image coding; Production; Dynamic range; Brightness; Extraterrestrial measurements
	Abstract	In the quality evaluation of high dynamic range and wide color gamut (HDR/WCG) images, a number of works have concluded that native HDR metrics, such as HDR visual difference predictor (HDR-VDP), HDR video quality metric (HDR-VQM), or convolutional neural network (CNN)-based visibility metrics for HDR content, provide the best results. These metrics consider only the luminance component, but several color difference metrics have been specifically developed for, and validated with, HDR/WCG images. In this paper, we perform subjective evaluation experiments in a professional HDR/WCG production setting, under a real use case scenario. The results are quite relevant in that they show, firstly, that the performance of HDR metrics is worse than that of a classic, simple standard dynamic range (SDR) metric applied directly to the HDR content; and secondly, that the chrominance metrics specifically developed for HDR/WCG imaging have poor correlation with observer scores and are also outperformed by an SDR metric. Based on these findings, we show how a very simple framework for creating color HDR metrics, that uses only luminance SDR metrics, transfer functions, and classic color spaces, is able to consistently outperform, by a considerable margin, state-of-the-art HDR metrics on a varied set of HDR content, for both perceptual quantization (PQ) and Hybrid Log-Gamma (HLG) encoding, luminance and chroma distortions, and on different color spaces of common use.
	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	600.161; 611.007			Approved	no
	Call Number	Admin @ si @ SVG2022			Serial	3683
Permanent link to this record



	Author	Pau Torras; Arnau Baro; Alicia Fornes; Lei Kang
	Title	Improving Handwritten Music Recognition through Language Model Integration			Type	Conference Article
	Year	2022	Publication	4th International Workshop on Reading Music Systems (WoRMS2022)	Abbreviated Journal
	Volume		Issue		Pages	42-46
	Keywords	optical music recognition; historical sources; diversity; music theory; digital humanities
	Abstract	Handwritten Music Recognition, especially in the historical domain, is an inherently challenging endeavour; paper degradation artefacts and the ambiguous nature of handwriting make recognising such scores an error-prone process, even for the current state-of-the-art Sequence to Sequence models. In this work we propose a way of reducing the production of statistically implausible output sequences by fusing a Language Model into a recognition Sequence to Sequence model. The idea is leveraging visually-conditioned and context-conditioned output distributions in order to automatically find and correct any mistakes that would otherwise break context significantly. We have found this approach to improve recognition results to 25.15 SER (%) from a previous best of 31.79 SER (%) in the literature.
	Address	November 18, 2022
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference	WoRMS
	Notes	DAG; 600.121; 600.162; 602.230			Approved	no
	Call Number	Admin @ si @ TBF2022			Serial	3735
Permanent link to this record



	Author	Guillermo Torres; Sonia Baeza; Carles Sanchez; Ignasi Guasch; Antoni Rosell; Debora Gil
	Title	An Intelligent Radiomic Approach for Lung Cancer Screening			Type	Journal Article
	Year	2022	Publication	Applied Sciences	Abbreviated Journal	APPLSCI
	Volume	12	Issue	3	Pages	1568
	Keywords	Lung cancer; Early diagnosis; Screening; Neural networks; Image embedding; Architecture optimization
	Abstract	The efficiency of lung cancer screening for reducing mortality is hindered by the high rate of false positives. Artificial intelligence applied to radiomics could help to early discard benign cases from the analysis of CT scans. The available amount of data and the fact that benign cases are a minority, constitutes a main challenge for the successful use of state of the art methods (like deep learning), which can be biased, over-fitted and lack of clinical reproducibility. We present an hybrid approach combining the potential of radiomic features to characterize nodules in CT scans and the generalization of the feed forward networks. In order to obtain maximal reproducibility with minimal training data, we propose an embedding of nodules based on the statistical significance of radiomic features for malignancy detection. This representation space of lesions is the input to a feed forward network, which architecture and hyperparameters are optimized using own-defined metrics of the diagnostic power of the whole system. Results of the best model on an independent set of patients achieve 100% of sensitivity and 83% of specificity (AUC = 0.94) for malignancy detection.
	Address	Jan 2022
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	IAM; 600.139; 600.145			Approved	no
	Call Number	Admin @ si @ TBS2022			Serial	3699
Permanent link to this record



	Author	Penny Tarling; Mauricio Cantor; Albert Clapes; Sergio Escalera
	Title	Deep learning with self-supervision and uncertainty regularization to count fish in underwater images			Type	Journal Article
	Year	2022	Publication	PloS One	Abbreviated Journal	Plos
	Volume	17	Issue	5	Pages	e0267759
	Keywords
	Abstract	Effective conservation actions require effective population monitoring. However, accurately counting animals in the wild to inform conservation decision-making is difficult. Monitoring populations through image sampling has made data collection cheaper, wide-reaching and less intrusive but created a need to process and analyse this data efficiently. Counting animals from such data is challenging, particularly when densely packed in noisy images. Attempting this manually is slow and expensive, while traditional computer vision methods are limited in their generalisability. Deep learning is the state-of-the-art method for many computer vision tasks, but it has yet to be properly explored to count animals. To this end, we employ deep learning, with a density-based regression approach, to count fish in low-resolution sonar images. We introduce a large dataset of sonar videos, deployed to record wild Lebranche mullet schools (Mugil liza), with a subset of 500 labelled images. We utilise abundant unlabelled data in a self-supervised task to improve the supervised counting task. For the first time in this context, by introducing uncertainty quantification, we improve model training and provide an accompanying measure of prediction uncertainty for more informed biological decision-making. Finally, we demonstrate the generalisability of our proposed counting framework through testing it on a recent benchmark dataset of high-resolution annotated underwater images from varying habitats (DeepFish). From experiments on both contrasting datasets, we demonstrate our network outperforms the few other deep learning models implemented for solving this task. By providing an open-source framework along with training data, our study puts forth an efficient deep learning template for crowd counting aquatic animals thereby contributing effective methods to assess natural populations from the ever-increasing visual data.
	Address
	Corporate Author				Thesis
	Publisher	Public Library of Science	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	HuPBA			Approved	no
	Call Number	Admin @ si @ TCC2022			Serial	3743
Permanent link to this record



	Author	Michael Teutsch; Angel Sappa; Riad I. Hammoud
	Title	Image and Video Enhancement			Type	Book Chapter
	Year	2022	Publication	Computer Vision in the Infrared Spectrum. Synthesis Lectures on Computer Vision	Abbreviated Journal
	Volume		Issue		Pages	9-21
	Keywords
	Abstract	Image and video enhancement aims at improving the signal quality relative to imaging artifacts such as noise and blur or atmospheric perturbations such as turbulence and haze. It is usually performed in order to assist humans in analyzing image and video content or simply to present humans visually appealing images and videos. However, image and video enhancement can also be used as a preprocessing technique to ease the task and thus improve the performance of subsequent automatic image content analysis algorithms: preceding dehazing can improve object detection as shown by [23] or explicit turbulence modeling can improve moving object detection as discussed by [24]. But it remains an open question whether image and video enhancement should rather be performed explicitly as a preprocessing step or implicitly for example by feeding affected images directly to a neural network for image content analysis like object detection [25]. Especially for real-time video processing at low latency it can be better to handle image perturbation implicitly in order to minimize the processing time of an algorithm. This can be achieved by making algorithms for image content analysis robust or even invariant to perturbations such as noise or blur. Additionally, mistakes of an individual preprocessing module can obviously affect the quality of the entire processing pipeline.
	Address
	Corporate Author				Thesis
	Publisher	Springer	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	SLCV
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	MSIAU; MACO			Approved	no
	Call Number	Admin @ si @ TSH2022a			Serial	3807
Permanent link to this record



	Author	Michael Teutsch; Angel Sappa; Riad I. Hammoud
	Title	Cross-Spectral Image Processing			Type	Book Chapter
	Year	2022	Publication	Computer Vision in the Infrared Spectrum. Synthesis Lectures on Computer Vision	Abbreviated Journal
	Volume		Issue		Pages	23-34
	Keywords
	Abstract	Although this book is on IR computer vision and its main focus lies on IR image and video processing and analysis, a special attention is dedicated to cross-spectral image processing due to the increasing number of publications and applications in this domain. In these cross-spectral frameworks, IR information is used together with information from other spectral bands to tackle some specific problems by developing more robust solutions. Tasks considered for cross-spectral processing are for instance dehazing, segmentation, vegetation index estimation, or face recognition. This increasing number of applications is motivated by cross- and multi-spectral camera setups available already on the market like for example smartphones, remote sensing multispectral cameras, or multi-spectral cameras for automotive systems or drones. In this chapter, different cross-spectral image processing techniques will be reviewed together with possible applications. Initially, image registration approaches for the cross-spectral case are reviewed: the registration stage is the first image processing task, which is needed to align images acquired by different sensors within the same reference coordinate system. Then, recent cross-spectral image colorization approaches, which are intended to colorize infrared images for different applications are presented. Finally, the cross-spectral image enhancement problem is tackled by including guided super resolution techniques, image dehazing approaches, cross-spectral filtering and edge detection. Figure 3.1 illustrates cross-spectral image processing stages as well as their possible connections. Table 3.1 presents some of the available public cross-spectral datasets generally used as reference data to evaluate cross-spectral image registration, colorization, enhancement, or exploitation results.
	Address
	Corporate Author				Thesis
	Publisher	Springer	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	SLCV
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-3-031-00698-2	Medium
	Area		Expedition		Conference
	Notes	MSIAU; MACO			Approved	no
	Call Number	Admin @ si @ TSH2022b			Serial	3805
Permanent link to this record



	Author	Michael Teutsch; Angel Sappa; Riad I. Hammoud
	Title	Detection, Classification, and Tracking			Type	Book Chapter
	Year	2022	Publication	Computer Vision in the Infrared Spectrum. Synthesis Lectures on Computer Vision	Abbreviated Journal
	Volume		Issue		Pages	35-58
	Keywords
	Abstract	Automatic image and video exploitation or content analysis is a technique to extract higher-level information from a scene such as objects, behavior, (inter-)actions, environment, or even weather conditions. The relevant information is assumed to be contained in the two-dimensional signal provided in an image (width and height in pixels) or the three-dimensional signal provided in a video (width, height, and time). But also intermediate-level information such as object classes [196], locations [197], or motion [198] can help applications to fulfill certain tasks such as intelligent compression [199], video summarization [200], or video retrieval [201]. Usually, videos with their temporal dimension are a richer source of data compared to single images [202] and thus certain video content can be extracted from videos only such as object motion or object behavior. Often, machine learning or nowadays deep learning techniques are utilized to model prior knowledge about object or scene appearance using labeled training samples [203, 204]. After a learning phase, these models are then applied in real world applications, which is called inference.
	Address
	Corporate Author				Thesis
	Publisher	Springer	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	SLCV
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-3-031-00698-2	Medium
	Area		Expedition		Conference
	Notes	MSIAU; MACO			Approved	no
	Call Number	Admin @ si @ TSH2022c			Serial	3806
Permanent link to this record



	Author	Emanuele Vivoli; Ali Furkan Biten; Andres Mafla; Dimosthenis Karatzas; Lluis Gomez
	Title	MUST-VQA: MUltilingual Scene-text VQA			Type	Conference Article
	Year	2022	Publication	Proceedings European Conference on Computer Vision Workshops	Abbreviated Journal
	Volume	13804	Issue		Pages	345–358
	Keywords	Visual question answering; Scene text; Translation robustness; Multilingual models; Zero-shot transfer; Power of language models
	Abstract	In this paper, we present a framework for Multilingual Scene Text Visual Question Answering that deals with new languages in a zero-shot fashion. Specifically, we consider the task of Scene Text Visual Question Answering (STVQA) in which the question can be asked in different languages and it is not necessarily aligned to the scene text language. Thus, we first introduce a natural step towards a more generalized version of STVQA: MUST-VQA. Accounting for this, we discuss two evaluation scenarios in the constrained setting, namely IID and zero-shot and we demonstrate that the models can perform on a par on a zero-shot setting. We further provide extensive experimentation and show the effectiveness of adapting multilingual language models into STVQA tasks.
	Address	Tel-Aviv; Israel; October 2022
	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	ECCVW
	Notes	DAG; 302.105; 600.155; 611.002			Approved	no
	Call Number	Admin @ si @ VBM2022			Serial	3770
Permanent link to this record



	Author	Diego Velazquez; Pau Rodriguez; Josep M. Gonfaus; Xavier Roca; Jordi Gonzalez
	Title	A Closer Look at Embedding Propagation for Manifold Smoothing			Type	Journal Article
	Year	2022	Publication	Journal of Machine Learning Research	Abbreviated Journal	JMLR
	Volume	23	Issue	252	Pages	1-27
	Keywords	Regularization; emi-supervised learning; self-supervised learning; adversarial robustness; few-shot classification
	Abstract	Supervised training of neural networks requires a large amount of manually annotated data and the resulting networks tend to be sensitive to out-of-distribution (OOD) data. Self- and semi-supervised training schemes reduce the amount of annotated data required during the training process. However, OOD generalization remains a major challenge for most methods. Strategies that promote smoother decision boundaries play an important role in out-of-distribution generalization. For example, embedding propagation (EP) for manifold smoothing has recently shown to considerably improve the OOD performance for few-shot classification. EP achieves smoother class manifolds by building a graph from sample embeddings and propagating information through the nodes in an unsupervised manner. In this work, we extend the original EP paper providing additional evidence and experiments showing that it attains smoother class embedding manifolds and improves results in settings beyond few-shot classification. Concretely, we show that EP improves the robustness of neural networks against multiple adversarial attacks as well as semi- and self-supervised learning performance.
	Address	9/2022
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes				Approved	no
	Call Number	Admin @ si @ VRG2022			Serial	3762
Permanent link to this record



	Author	Henry Velesaca; Patricia Suarez; Dario Carpio; Rafael E. Rivadeneira; Angel Sanchez; Angel Morera
	Title	Video Analytics in Urban Environments: Challenges and Approaches			Type	Book Chapter
	Year	2022	Publication	ICT Applications for Smart Cities	Abbreviated Journal
	Volume	224	Issue		Pages	101-121
	Keywords
	Abstract	This chapter reviews state-of-the-art approaches generally present in the pipeline of video analytics on urban scenarios. A typical pipeline is used to cluster approaches in the literature, including image preprocessing, object detection, object classification, and object tracking modules. Then, a review of recent approaches for each module is given. Additionally, applications and datasets generally used for training and evaluating the performance of these approaches are included. This chapter does not pretend to be an exhaustive review of state-of-the-art video analytics in urban environments but rather an illustration of some of the different recent contributions. The chapter concludes by presenting current trends in video analytics in the urban scenario field.
	Address	September 2022
	Corporate Author				Thesis
	Publisher	Springer	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	ISRL
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-3-031-06306-0	Medium
	Area		Expedition		Conference
	Notes	MSIAU; MACO			Approved	no
	Call Number	Admin @ si @ VSC2022			Serial	3811
Permanent link to this record



	Author	Henry Velesaca; Patricia Suarez; Angel Sappa; Dario Carpio; Rafael E. Rivadeneira; Angel Sanchez
	Title	Review on Common Techniques for Urban Environment Video Analytics			Type	Conference Article
	Year	2022	Publication	Anais do III Workshop Brasileiro de Cidades Inteligentes	Abbreviated Journal
	Volume		Issue		Pages	107-118
	Keywords	Video Analytics; Review; Urban Environments; Smart Cities
	Abstract	This work compiles the different computer vision-based approaches from the state-of-the-art intended for video analytics in urban environments. The manuscript groups the different approaches according to the typical modules present in video analysis, including image preprocessing, object detection, classification, and tracking. This proposed pipeline serves as a basic guide to representing these most representative approaches in this topic of video analysis that will be addressed in this work. Furthermore, the manuscript is not intended to be an exhaustive review of the most advanced approaches, but only a list of common techniques proposed to address recurring problems in this field.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference	WBCI
	Notes	MSIAU; 601.349			Approved	no
	Call Number	Admin @ si @ VSS2022			Serial	3773
Permanent link to this record



	Author	Kai Wang
	Title	Continual learning for hierarchical classification, few-shot recognition, and multi-modal learning			Type	Book Whole
	Year	2022	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Deep learning has drastically changed computer vision in the past decades and achieved great success in many applications, such as image classification, retrieval, detection, and segmentation thanks to the emergence of neural networks. Typically, for most applications, these networks are presented with examples from all tasks they are expected to perform. However, for many applications, this is not a realistic scenario, and an algorithm is required to learn tasks sequentially. Continual learning proposes theory and methods for this scenario. The main challenge for continual learning systems is called catastrophic forgetting and refers to a significant drop in performance on previous tasks. To tackle this problem, three main branches of methods have been explored to alleviate the forgetting in continual learning. They are regularization-based methods, rehearsalbased methods, and parameter isolation-based methods. However, most of them are focused on image classification tasks. Continual learning of many computer vision fields has still not been well-explored. Thus, in this thesis, we extend the continual learning knowledge to meta learning, we propose a method for the incremental learning of hierarchical relations for image classification, we explore image recognition in online continual learning, and study continual learning for cross-modal learning. In this thesis, we explore the usage of image rehearsal when addressing the incremental meta learning problem. Observing that existingmethods fail to improve performance with saved exemplars, we propose to mix exemplars with current task data and episode-level distillation to overcome forgetting in incremental meta learning. Next, we study a more realistic image classification scenario where each class has multiple granularity levels. Only one label is present at any time, which requires the model to infer if the provided label has a hierarchical relation with any already known label. In experiments, we show that the estimated hierarchy information can be beneficial in both the training and inference stage. For the online continual learning setting, we investigate the usage of intermediate feature replay. In this case, the training samples are only observed by the model only one time. Here we fix thememory buffer for feature replay and compare the effectiveness of saving features from different layers. Finally, we investigate multi-modal continual learning, where an image encoder is cooperating with a semantic branch. We consider the continual learning of both zero-shot learning and cross-modal retrieval problems.
	Address	July, 2022
	Corporate Author				Thesis	Ph.D. thesis
	Publisher		Place of Publication		Editor	Luis Herranz;Joost Van de Weijer
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-124793-2-4	Medium
	Area		Expedition		Conference
	Notes	LAMP			Approved	no
	Call Number	Admin @ si @ Wan2022			Serial	3714
Permanent link to this record