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	Josep Brugues Pujolras; Lluis Gomez; Dimosthenis Karatzas
	Title	A Multilingual Approach to Scene Text Visual Question Answering			Type	Conference Article
	Year	2022	Publication	Document Analysis Systems.15th IAPR International Workshop, (DAS2022)	Abbreviated Journal
	Volume		Issue		Pages	65-79
	Keywords	Scene text; Visual question answering; Multilingual word embeddings; Vision and language; Deep learning
	Abstract	Scene Text Visual Question Answering (ST-VQA) has recently emerged as a hot research topic in Computer Vision. Current ST-VQA models have a big potential for many types of applications but lack the ability to perform well on more than one language at a time due to the lack of multilingual data, as well as the use of monolingual word embeddings for training. In this work, we explore the possibility to obtain bilingual and multilingual VQA models. In that regard, we use an already established VQA model that uses monolingual word embeddings as part of its pipeline and substitute them by FastText and BPEmb multilingual word embeddings that have been aligned to English. Our experiments demonstrate that it is possible to obtain bilingual and multilingual VQA models with a minimal loss in performance in languages not used during training, as well as a multilingual model trained in multiple languages that match the performance of the respective monolingual baselines.
	Address	La Rochelle, France; May 22–25, 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	DAS
	Notes	DAG; 611.004; 600.155; 601.002			Approved	no
	Call Number	Admin @ si @ BGK2022b			Serial	3695
Permanent link to this record



	Author	Adria Molina; Lluis Gomez; Oriol Ramos Terrades; Josep Llados
	Title	A Generic Image Retrieval Method for Date Estimation of Historical Document Collections			Type	Conference Article
	Year	2022	Publication	Document Analysis Systems.15th IAPR International Workshop, (DAS2022)	Abbreviated Journal
	Volume	13237	Issue		Pages	583–597
	Keywords	Date estimation; Document retrieval; Image retrieval; Ranking loss; Smooth-nDCG
	Abstract	Date estimation of historical document images is a challenging problem, with several contributions in the literature that lack of the ability to generalize from one dataset to others. This paper presents a robust date estimation system based in a retrieval approach that generalizes well in front of heterogeneous collections. We use a ranking loss function named smooth-nDCG to train a Convolutional Neural Network that learns an ordination of documents for each problem. One of the main usages of the presented approach is as a tool for historical contextual retrieval. It means that scholars could perform comparative analysis of historical images from big datasets in terms of the period where they were produced. We provide experimental evaluation on different types of documents from real datasets of manuscript and newspaper images.
	Address	La Rochelle, France; May 22–25, 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	DAS
	Notes	DAG; 600.140; 600.121			Approved	no
	Call Number	Admin @ si @ MGR2022			Serial	3694
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	Jorge Charco; Angel Sappa; Boris X. Vintimilla; Henry Velesaca
	Title	Human Body Pose Estimation in Multi-view Environments			Type	Book Chapter
	Year	2022	Publication	ICT Applications for Smart Cities. Intelligent Systems Reference Library	Abbreviated Journal
	Volume	224	Issue		Pages	79-99
	Keywords
	Abstract	This chapter tackles the challenging problem of human pose estimation in multi-view environments to handle scenes with self-occlusions. The proposed approach starts by first estimating the camera pose—extrinsic parameters—in multi-view scenarios; due to few real image datasets, different virtual scenes are generated by using a special simulator, for training and testing the proposed convolutional neural network based approaches. Then, these extrinsic parameters are used to establish the relation between different cameras into the multi-view scheme, which captures the pose of the person from different points of view at the same time. The proposed multi-view scheme allows to robustly estimate human body joints’ position even in situations where they are occluded. This would help to avoid possible false alarms in behavioral analysis systems of smart cities, as well as applications for physical therapy, safe moving assistance for the elderly among other. The chapter concludes by presenting experimental results in real scenes by using state-of-the-art and the proposed multi-view approaches.
	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 @ CSV2022b			Serial	3810
Permanent link to this record



	Author	Victoria Ruiz; Angel Sanchez; Jose F. Velez; Bogdan Raducanu
	Title	Waste Classification with Small Datasets and Limited Resources			Type	Book Chapter
	Year	2022	Publication	ICT Applications for Smart Cities. Intelligent Systems Reference Library	Abbreviated Journal
	Volume	224	Issue		Pages	185-203
	Keywords
	Abstract	Automatic waste recycling has become a very important societal challenge nowadays, raising people’s awareness for a cleaner environment and a more sustainable lifestyle. With the transition to Smart Cities, and thanks to advanced ICT solutions, this problem has received a new impulse. The waste recycling focus has shifted from general waste treating facilities to an individual responsibility, where each person should become aware of selective waste separation. The surge of the mobile devices, accompanied by a significant increase in computation power, has potentiated and facilitated this individual role. An automated image-based waste classification mechanism can help with a more efficient recycling and a reduction of contamination from residuals. Despite the good results achieved with the deep learning methodologies for this task, the Achille’s heel is that they require large neural networks which need significant computational resources for training and therefore are not suitable for mobile devices. To circumvent this apparently intractable problem, we will rely on knowledge distillation in order to transfer the network’s knowledge from a larger network (called ‘teacher’) to a smaller, more compact one, (referred as ‘student’) and thus making it possible the task of image classification on a device with limited resources. For evaluation, we considered as ‘teachers’ large architectures such as InceptionResNet or DenseNet and as ‘students’, several configurations of the MobileNets. We used the publicly available TrashNet dataset to demonstrate that the distillation process does not significantly affect system’s performance (e.g. classification accuracy) of the student network.
	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	LAMP			Approved	no
	Call Number	Admin @ si @			Serial	3813
Permanent link to this record



	Author	Angel Sappa (ed)
	Title	ICT Applications for Smart Cities			Type	Book Whole
	Year	2022	Publication	ICT Applications for Smart Cities	Abbreviated Journal
	Volume	224	Issue		Pages
	Keywords	Computational Intelligence; Intelligent Systems; Smart Cities; ICT Applications; Machine Learning; Pattern Recognition; Computer Vision; Image Processing
	Abstract	Part of the book series: Intelligent Systems Reference Library (ISRL) This book is the result of four-year work in the framework of the Ibero-American Research Network TICs4CI funded by the CYTED program. In the following decades, 85% of the world's population is expected to live in cities; hence, urban centers should be prepared to provide smart solutions for problems ranging from video surveillance and intelligent mobility to the solid waste recycling processes, just to mention a few. More specifically, the book describes underlying technologies and practical implementations of several successful case studies of ICTs developed in the following smart city areas: • Urban environment monitoring • Intelligent mobility • Waste recycling processes • Video surveillance • Computer-aided diagnose in healthcare systems • Computer vision-based approaches for efficiency in production processes The book is intended for researchers and engineers in the field of ICTs for smart cities, as well as to anyone who wants to know about state-of-the-art approaches and challenges on this field.
	Address	September 2022
	Corporate Author				Thesis
	Publisher	Springer	Place of Publication		Editor	Angel Sappa
	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 @ Sap2022			Serial	3812
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	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	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	Vacit Oguz Yazici
	Title	Towards Smart Fashion: Visual Recognition of Products and Attributes			Type	Book Whole
	Year	2022	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Artificial intelligence is innovating the fashion industry by proposing new applications and solutions to the problems encountered by researchers and engineers working in the industry. In this thesis, we address three of these problems. In the first part of the thesis, we tackle the problem of multi-label image classification which is very related to fashion attribute recognition. In the second part of the thesis, we address two problems that are specific to fashion. Firstly, we address the problem of main product detection which is the task of associating correct image parts (e.g. bounding boxes) with the fashion product being sold. Secondly, we address the problem of color naming for multicolored fashion items. The task of multi-label image classification consists in assigning various concepts such as objects or attributes to images. Usually, there are dependencies that can be learned between the concepts to capture label correlations (chair and table classes are more likely to co-exist than chair and giraffe). If we treat the multi-label image classification problem as an orderless set prediction problem, we can exploit recurrent neural networks (RNN) to capture label correlations. However, RNNs are trained to predict ordered sequences of tokens, so if the order of the predicted sequence is different than the order of the ground truth sequence, there will be penalization although the predictions are correct. Therefore, in the first part of the thesis, we propose an orderless loss function which will order the labels in the ground truth sequence dynamically in a way that the minimum loss is achieved. This results in a significant improvement of RNN models on multi-label image classification over the previous methods. However, RNNs suffer from long term dependencies when the cardinality of set grows bigger. The decoding process might stop early if the current hidden state cannot find any object and outputs the termination token. This would cause the remaining classes not to be predicted and lower recall metric. Transformers can be used to avoid the long term dependency problem exploiting their selfattention modules that process sequential data simultaneously. Consequently, we propose a novel transformer model for multi-label image classification which surpasses the state-of-the-art results by a large margin. In the second part of thesis, we focus on two fashion-specific problems. Main product detection is the task of associating image parts with the fashion product that is being sold, generally using associated textual metadata (product title or description). Normally, in fashion e-commerces, products are represented by multiple images where a person wears the product along with other fashion items. If all the fashion items in the images are marked with bounding boxes, we can use the textual metadata to decide which item is the main product. The initial work treated each of these images independently, discarding the fact that they all belong to the same product. In this thesis, we represent the bounding boxes from all the images as nodes in a fully connected graph. This allows the algorithm to learn relations between the nodes during training and take the entire context into account for the final decision. Our algorithm results in a significant improvement of the state-ofthe-art. Moreover, we address the problem of color naming for multicolored fashion items, which is a challenging task due to the external factors such as illumination changes or objects that act as clutter. In the context of multi-label classification, the vaguely defined lines between the classes in the color space cause ambiguity. For example, a shade of blue which is very close to green might cause the model to incorrectly predict the color blue and green at the same time. Based on this, models trained for color naming are expected to recognize the colors and their quantities in both single colored and multicolored fashion items. Therefore, in this thesis, we propose a novel architecture with an additional head that explicitly estimates the number of colors in fashion items. This removes the ambiguity problem and results in better color naming performance.
	Address	January 2022
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	IMPRIMA	Place of Publication		Editor	Joost Van de Weijer;Arnau Ramisa
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-122714-6-1	Medium
	Area		Expedition		Conference
	Notes	LAMP			Approved	no
	Call Number	Admin @ si @ Ogu2022			Serial	3631
Permanent link to this record



	Author	Akhil Gurram
	Title	Monocular Depth Estimation for Autonomous Driving			Type	Book Whole
	Year	2022	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	3D geometric information is essential for on-board perception in autonomous driving and driver assistance. Autonomous vehicles (AVs) are equipped with calibrated sensor suites. As part of these suites, we can find LiDARs, which are expensive active sensors in charge of providing the 3D geometric information. Depending on the operational conditions for the AV, calibrated stereo rigs may be also sufficient for obtaining 3D geometric information, being these rigs less expensive and easier to install than LiDARs. However, ensuring a proper maintenance and calibration of these types of sensors is not trivial. Accordingly, there is an increasing interest on performing monocular depth estimation (MDE) to obtain 3D geometric information on-board. MDE is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Moreover, a set of single cameras with MDE capabilities would still be a cheap solution for on-board perception, relatively easy to integrate and maintain in an AV. Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Accordingly, the overall goal of this PhD is to study methods for improving CNN-based MDE accuracy under different training settings. More specifically, this PhD addresses different research questions that are described below. When we started to work in this PhD, state-of-theart methods for MDE were already based on CNNs. In fact, a promising line of work consisted in using image-based semantic supervision (i.e., pixel-level class labels) while training CNNs for MDE using LiDAR-based supervision (i.e., depth). It was common practice to assume that the same raw training data are complemented by both types of supervision, i.e., with depth and semantic labels. However, in practice, it was more common to find heterogeneous datasets with either only depth supervision or only semantic supervision. Therefore, our first work was to research if we could train CNNs for MDE by leveraging depth and semantic information from heterogeneous datasets. We show that this is indeed possible, and we surpassed the state-of-the-art results on MDE at the time we did this research. To achieve our results, we proposed a particular CNN architecture and a new training protocol. After this research, it was clear that the upper-bound setting to train CNN-based MDE models consists in using LiDAR data as supervision. However, it would be cheaper and more scalable if we would be able to train such models from monocular sequences. Obviously, this is far more challenging, but worth to research. Training MDE models using monocular sequences is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. To alleviate these problems, we perform MDE by virtual-world supervision and real-world SfM self-supervision. We call our proposalMonoDEVSNet. We compensate the SfM self-supervision limitations by leveraging virtual-world images with accurate semantic and depth supervision, as well as addressing the virtual-to-real domain gap. MonoDEVSNet outperformed previous MDE CNNs trained on monocular and even stereo sequences. We have publicly released MonoDEVSNet at <https://github.com/HMRC-AEL/MonoDEVSNet>. Finally, since MDE is performed to produce 3D information for being used in downstream tasks related to on-board perception. We also address the question of whether the standard metrics for MDE assessment are a good indicator for future MDE-based driving-related perception tasks. By using 3D object detection on point clouds as proxy of on-board perception, we conclude that, indeed, MDE evaluation metrics give rise to a ranking of methods which reflects relatively well the 3D object detection results we may expect.
	Address	March, 2022
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	IMPRIMA	Place of Publication		Editor	Antonio Lopez;Onay Urfalioglu
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-124793-0-0	Medium
	Area		Expedition		Conference
	Notes	ADAS			Approved	no
	Call Number	Admin @ si @ Gur2022			Serial	3712
Permanent link to this record



	Author	Parichehr Behjati Ardakani
	Title	Towards Efficient and Robust Convolutional Neural Networks for Single Image Super-Resolution			Type	Book Whole
	Year	2022	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Single image super-resolution (SISR) is an important task in image processing which aims to enhance the resolution of imaging systems. Recently, SISR has witnessed great strides with the rapid development of deep learning. Recent advances in SISR are mostly devoted to designing deeper and wider networks to enhance their representation learning capacity. However, as the depth of networks increases, deep learning-based methods are faced with the challenge of computational complexity in practice. Moreover, most existing methods rarely leverage the intermediate features and also do not discriminate the computation of features by their frequencial components, thereby achieving relatively low performance. Aside from the aforementioned problems, another desired ability is to upsample images to arbitrary scales using a single model. Most current SISR methods train a dedicated model for each target resolution, losing generality and increasing memory requirements. In this thesis, we address the aforementioned issues and propose solutions to them: i) We present a novel frequency-based enhancement block which treats different frequencies in a heterogeneous way and also models inter-channel dependencies, which consequently enrich the output feature. Thus it helps the network generate more discriminative representations by explicitly recovering finer details. ii) We introduce OverNet which contains two main parts: a lightweight feature extractor that follows a novel recursive framework of skip and dense connections to reduce low-level feature degradation, and an overscaling module that generates an accurate SR image by internally constructing an overscaled intermediate representation of the output features. Then, to solve the problem of reconstruction at arbitrary scale factors, we introduce a novel multi-scale loss, that allows the simultaneous training of all scale factors using a single model. iii) We propose a directional variance attention network which leverages a novel attention mechanism to enhance features in different channels and spatial regions. Moreover, we introduce a novel procedure for using attention mechanisms together with residual blocks to facilitate the preservation of finer details. Finally, we demonstrate that our approaches achieve considerably better performance than previous state-of-the-art methods, in terms of both quantitative and visual quality.
	Address	April, 2022
	Corporate Author				Thesis	Ph.D. thesis
	Publisher		Place of Publication		Editor	Jordi Gonzalez;Xavier Roca;Pau Rodriguez
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-124793-1-7	Medium
	Area		Expedition		Conference
	Notes	ISE			Approved	no
	Call Number	Admin @ si @ Beh2022			Serial	3713
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



	Author	Aitor Alvarez-Gila
	Title	Self-supervised learning for image-to-image translation in the small data regime			Type	Book Whole
	Year	2022	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords	Computer vision; Neural networks; Self-supervised learning; Image-to-image mapping; Probabilistic programming
	Abstract	The mass irruption of Deep Convolutional Neural Networks (CNNs) in computer vision since 2012 led to a dominance of the image understanding paradigm consisting in an end-to-end fully supervised learning workflow over large-scale annotated datasets. This approach proved to be extremely useful at solving a myriad of classic and new computer vision tasks with unprecedented performance —often, surpassing that of humans—, at the expense of vast amounts of human-labeled data, extensive computational resources and the disposal of all of our prior knowledge on the task at hand. Even though simple transfer learning methods, such as fine-tuning, have achieved remarkable impact, their success when the amount of labeled data in the target domain is small is limited. Furthermore, the non-static nature of data generation sources will often derive in data distribution shifts that degrade the performance of deployed models. As a consequence, there is a growing demand for methods that can exploit elements of prior knowledge and sources of information other than the manually generated ground truth annotations of the images during the network training process, so that they can adapt to new domains that constitute, if not a small data regime, at least a small labeled data regime. This thesis targets such few or no labeled data scenario in three distinct image-to-image mapping learning problems. It contributes with various approaches that leverage our previous knowledge of different elements of the image formation process: We first present a data-efficient framework for both defocus and motion blur detection, based on a model able to produce realistic synthetic local degradations. The framework comprises a self-supervised, a weakly-supervised and a semi-supervised instantiation, depending on the absence or availability and the nature of human annotations, and outperforms fully-supervised counterparts in a variety of settings. Our knowledge on color image formation is then used to gather input and target ground truth image pairs for the RGB to hyperspectral image reconstruction task. We make use of a CNN to tackle this problem, which, for the first time, allows us to exploit spatial context and achieve state-of-the-art results given a limited hyperspectral image set. In our last contribution to the subfield of data-efficient image-to-image transformation problems, we present the novel semi-supervised task of zero-pair cross-view semantic segmentation: we consider the case of relocation of the camera in an end-to-end trained and deployed monocular, fixed-view semantic segmentation system often found in industry. Under the assumption that we are allowed to obtain an additional set of synchronized but unlabeled image pairs of new scenes from both original and new camera poses, we present ZPCVNet, a model and training procedure that enables the production of dense semantic predictions in either source or target views at inference time. The lack of existing suitable public datasets to develop this approach led us to the creation of MVMO, a large-scale Multi-View, Multi-Object path-traced dataset with per-view semantic segmentation annotations. We expect MVMO to propel future research in the exciting under-developed fields of cross-view and multi-view semantic segmentation. Last, in a piece of applied research of direct application in the context of process monitoring of an Electric Arc Furnace (EAF) in a steelmaking plant, we also consider the problem of simultaneously estimating the temperature and spectral emissivity of distant hot emissive samples. To that end, we design our own capturing device, which integrates three point spectrometers covering a wide range of the Ultra-Violet, visible, and Infra-Red spectra and is capable of registering the radiance signal incoming from an 8cm diameter spot located up to 20m away. We then define a physically accurate radiative transfer model that comprises the effects of atmospheric absorbance, of the optical system transfer function, and of the sample temperature and spectral emissivity themselves. We solve this inverse problem without the need for annotated data using a probabilistic programming-based Bayesian approach, which yields full posterior distribution estimates of the involved variables that are consistent with laboratory-grade measurements.
	Address	Julu, 2019
	Corporate Author				Thesis	Ph.D. thesis
	Publisher		Place of Publication		Editor	Joost Van de Weijer; Estibaliz Garrote
	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			Approved	no
	Call Number	Admin @ si @ Alv2022			Serial	3716
Permanent link to this record



	Author	Idoia Ruiz
	Title	Deep Metric Learning for re-identification, tracking and hierarchical novelty detection			Type	Book Whole
	Year	2022	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Metric learning refers to the problem in machine learning of learning a distance or similarity measurement to compare data. In particular, deep metric learning involves learning a representation, also referred to as embedding, such that in the embedding space data samples can be compared based on the distance, directly providing a similarity measure. This step is necessary to perform several tasks in computer vision. It allows to perform the classification of images, regions or pixels, re-identification, out-of-distribution detection, object tracking in image sequences and any other task that requires computing a similarity score for their solution. This thesis addresses three specific problems that share this common requirement. The first one is person re-identification. Essentially, it is an image retrieval task that aims at finding instances of the same person according to a similarity measure. We first compare in terms of accuracy and efficiency, classical metric learning to basic deep learning based methods for this problem. In this context, we also study network distillation as a strategy to optimize the trade-off between accuracy and speed at inference time. The second problem we contribute to is novelty detection in image classification. It consists in detecting samples of novel classes, i.e. never seen during training. However, standard novelty detection does not provide any information about the novel samples besides they are unknown. Aiming at more informative outputs, we take advantage from the hierarchical taxonomies that are intrinsic to the classes. We propose a metric learning based approach that leverages the hierarchical relationships among classes during training, being able to predict the parent class for a novel sample in such hierarchical taxonomy. Our third contribution is in multi-object tracking and segmentation. This joint task comprises classification, detection, instance segmentation and tracking. Tracking can be formulated as a retrieval problem to be addressed with metric learning approaches. We tackle the existing difficulty in academic research that is the lack of annotated benchmarks for this task. To this matter, we introduce the problem of weakly supervised multi-object tracking and segmentation, facing the challenge of not having available ground truth for instance segmentation. We propose a synergistic training strategy that benefits from the knowledge of the supervised tasks that are being learnt simultaneously.
	Address	July, 2022
	Corporate Author				Thesis	Ph.D. thesis
	Publisher		Place of Publication		Editor	Joan Serrat
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-124793-4-8	Medium
	Area		Expedition		Conference
	Notes	ADAS			Approved	no
	Call Number	Admin @ si @ Rui2022			Serial	3717
Permanent link to this record