Publicacions CVC -- Query Results

	Publicacions CVC Home \| Show All \| Simple Search \| Advanced Search \| Add Record \| Import	Login Quick Search: Field: contains: ...
	1321–1335 of 3413 records found matching your query (RSS):

Search & Display Options

Select All Deselect All

[71–80] << 81 82 83 84 85 86 87 88 89 90 >> [91–100]

List View

Citations

Details

	Records
	Author	Sagnik Das; Hassan Ahmed Sial; Ke Ma; Ramon Baldrich; Maria Vanrell; Dimitris Samaras
	Title	Intrinsic Decomposition of Document Images In-the-Wild			Type	Conference Article
	Year	2020	Publication	31st British Machine Vision Conference	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Automatic document content processing is affected by artifacts caused by the shape of the paper, non-uniform and diverse color of lighting conditions. Fully-supervised methods on real data are impossible due to the large amount of data needed. Hence, the current state of the art deep learning models are trained on fully or partially synthetic images. However, document shadow or shading removal results still suffer because: (a) prior methods rely on uniformity of local color statistics, which limit their application on real-scenarios with complex document shapes and textures and; (b) synthetic or hybrid datasets with non-realistic, simulated lighting conditions are used to train the models. In this paper we tackle these problems with our two main contributions. First, a physically constrained learning-based method that directly estimates document reflectance based on intrinsic image formation which generalizes to challenging illumination conditions. Second, a new dataset that clearly improves previous synthetic ones, by adding a large range of realistic shading and diverse multi-illuminant conditions, uniquely customized to deal with documents in-the-wild. The proposed architecture works in two steps. First, a white balancing module neutralizes the color of the illumination on the input image. Based on the proposed multi-illuminant dataset we achieve a good white-balancing in really difficult conditions. Second, the shading separation module accurately disentangles the shading and paper material in a self-supervised manner where only the synthetic texture is used as a weak training signal (obviating the need for very costly ground truth with disentangled versions of shading and reflectance). The proposed approach leads to significant generalization of document reflectance estimation in real scenes with challenging illumination. We extensively evaluate on the real benchmark datasets available for intrinsic image decomposition and document shadow removal tasks. Our reflectance estimation scheme, when used as a pre-processing step of an OCR pipeline, shows a 21% improvement of character error rate (CER), thus, proving the practical applicability. The data and code will be available at: https://github.com/cvlab-stonybrook/DocIIW.
	Address	Virtual; September 2020
	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	BMVC
	Notes	CIC; 600.087; 600.140; 600.118			Approved	no
	Call Number	Admin @ si @ DSM2020			Serial	3461
Permanent link to this record



	Author	Fernando Vilariño
	Title	3D Scanning of Capitals at Library Living Lab			Type	Book Whole
	Year	2019	Publication	“Living Lab Projects 2019”. ENoLL.	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	MV; DAG; 600.140; 600.121;SIAI			Approved	no
	Call Number	Admin @ si @ Vil2019c			Serial	3463
Permanent link to this record



	Author	Xinhang Song; Haitao Zeng; Sixian Zhang; Luis Herranz; Shuqiang Jiang
	Title	Generalized Zero-shot Learning with Multi-source Semantic Embeddings for Scene Recognition			Type	Conference Article
	Year	2020	Publication	28th ACM International Conference on Multimedia	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Recognizing visual categories from semantic descriptions is a promising way to extend the capability of a visual classifier beyond the concepts represented in the training data (i.e. seen categories). This problem is addressed by (generalized) zero-shot learning methods (GZSL), which leverage semantic descriptions that connect them to seen categories (e.g. label embedding, attributes). Conventional GZSL are designed mostly for object recognition. In this paper we focus on zero-shot scene recognition, a more challenging setting with hundreds of categories where their differences can be subtle and often localized in certain objects or regions. Conventional GZSL representations are not rich enough to capture these local discriminative differences. Addressing these limitations, we propose a feature generation framework with two novel components: 1) multiple sources of semantic information (i.e. attributes, word embeddings and descriptions), 2) region descriptions that can enhance scene discrimination. To generate synthetic visual features we propose a two-step generative approach, where local descriptions are sampled and used as conditions to generate visual features. The generated features are then aggregated and used together with real features to train a joint classifier. In order to evaluate the proposed method, we introduce a new dataset for zero-shot scene recognition with multi-semantic annotations. Experimental results on the proposed dataset and SUN Attribute dataset illustrate the effectiveness of the proposed method.
	Address	Virtual; October 2020
	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	ACM
	Notes	LAMP; 600.141; 600.120			Approved	no
	Call Number	Admin @ si @ SZZ2020			Serial	3465
Permanent link to this record



	Author	Kai Wang; Luis Herranz; Anjan Dutta; Joost Van de Weijer
	Title	Bookworm continual learning: beyond zero-shot learning and continual learning			Type	Conference Article
	Year	2020	Publication	Workshop TASK-CV 2020	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually. Thus BCL generalizes both continual learning (CL) and zero-shot learning (ZSL). We also propose the bidirectional imagination (BImag) framework to address BCL where features of both past and future classes are generated. We observe that conditioning the feature generator on attributes can actually harm the continual learning ability, and propose two variants (joint class-attribute conditioning and asymmetric generation) to alleviate this problem.
	Address	Virtual; August 2020
	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	ECCVW
	Notes	LAMP; 600.141; 600.120			Approved	no
	Call Number	Admin @ si @ WHD2020			Serial	3466
Permanent link to this record



	Author	Carola Figueroa Flores
	Title	Visual Saliency for Object Recognition, and Object Recognition for Visual Saliency			Type	Book Whole
	Year	2021	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords	computer vision; visual saliency; fine-grained object recognition; convolutional neural networks; images classification
	Abstract	For humans, the recognition of objects is an almost instantaneous, precise and extremely adaptable process. Furthermore, we have the innate capability to learn new object classes from only few examples. The human brain lowers the complexity of the incoming data by filtering out part of the information and only processing those things that capture our attention. This, mixed with our biological predisposition to respond to certain shapes or colors, allows us to recognize in a simple glance the most important or salient regions from an image. This mechanism can be observed by analyzing on which parts of images subjects place attention; where they fix their eyes when an image is shown to them. The most accurate way to record this behavior is to track eye movements while displaying images. Computational saliency estimation aims to identify to what extent regions or objects stand out with respect to their surroundings to human observers. Saliency maps can be used in a wide range of applications including object detection, image and video compression, and visual tracking. The majority of research in the field has focused on automatically estimating saliency maps given an input image. Instead, in this thesis, we set out to incorporate saliency maps in an object recognition pipeline: we want to investigate whether saliency maps can improve object recognition results. In this thesis, we identify several problems related to visual saliency estimation. First, to what extent the estimation of saliency can be exploited to improve the training of an object recognition model when scarce training data is available. To solve this problem, we design an image classification network that incorporates saliency information as input. This network processes the saliency map through a dedicated network branch and uses the resulting characteristics to modulate the standard bottom-up visual characteristics of the original image input. We will refer to this technique as saliency-modulated image classification (SMIC). In extensive experiments on standard benchmark datasets for fine-grained object recognition, we show that our proposed architecture can significantly improve performance, especially on dataset with scarce training data. Next, we address the main drawback of the above pipeline: SMIC requires an explicit saliency algorithm that must be trained on a saliency dataset. To solve this, we implement a hallucination mechanism that allows us to incorporate the saliency estimation branch in an end-to-end trained neural network architecture that only needs the RGB image as an input. A side-effect of this architecture is the estimation of saliency maps. In experiments, we show that this architecture can obtain similar results on object recognition as SMIC but without the requirement of ground truth saliency maps to train the system. Finally, we evaluated the accuracy of the saliency maps that occur as a sideeffect of object recognition. For this purpose, we use a set of benchmark datasets for saliency evaluation based on eye-tracking experiments. Surprisingly, the estimated saliency maps are very similar to the maps that are computed from human eye-tracking experiments. Our results show that these saliency maps can obtain competitive results on benchmark saliency maps. On one synthetic saliency dataset this method even obtains the state-of-the-art without the need of ever having seen an actual saliency image for training.
	Address	March 2021
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	Ediciones Graficas Rey	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	978-84-122714-4-7	Medium
	Area		Expedition		Conference
	Notes	LAMP; 600.120			Approved	no
	Call Number	Admin @ si @ Fig2021			Serial	3600
Permanent link to this record



	Author	Debora Gil; Guillermo Torres
	Title	A multi-shape loss function with adaptive class balancing for the segmentation of lung structures			Type	Conference Article
	Year	2020	Publication	34th International Congress and Exhibition on Computer Assisted Radiology & Surgery	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract
	Address	Virtual; June 2020
	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	CARS
	Notes	IAM; 600.139; 600.145			Approved	no
	Call Number	Admin @ si @ GiT2020			Serial	3472
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	Conference Article
	Year	2020	Publication	Women in Geometry and Topology	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract
	Address	Barcelona; September 2019
	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; DAG; 600.139; 600.145; 600.121			Approved	no
	Call Number	Admin @ si @ GRP2020			Serial	3473
Permanent link to this record



	Author	Debora Gil; Katerine Diaz; Carles Sanchez; Aura Hernandez-Sabate
	Title	Early Screening of SARS-CoV-2 by Intelligent Analysis of X-Ray Images			Type	Miscellaneous
	Year	2020	Publication	Arxiv	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Future SARS-CoV-2 virus outbreak COVID-XX might possibly occur during the next years. However the pathology in humans is so recent that many clinical aspects, like early detection of complications, side effects after recovery or early screening, are currently unknown. In spite of the number of cases of COVID-19, its rapid spread putting many sanitary systems in the edge of collapse has hindered proper collection and analysis of the data related to COVID-19 clinical aspects. We describe an interdisciplinary initiative that integrates clinical research, with image diagnostics and the use of new technologies such as artificial intelligence and radiomics with the aim of clarifying some of SARS-CoV-2 open questions. The whole initiative addresses 3 main points: 1) collection of standardize data including images, clinical data and analytics; 2) COVID-19 screening for its early diagnosis at primary care centers; 3) define radiomic signatures of COVID-19 evolution and associated pathologies for the early treatment of complications. In particular, in this paper we present a general overview of the project, the experimental design and first results of X-ray COVID-19 detection using a classic approach based on HoG and feature selection. Our experiments include a comparison to some recent methods for COVID-19 screening in X-Ray and an exploratory analysis of the feasibility of X-Ray COVID-19 screening. Results show that classic approaches can outperform deep-learning methods in this experimental setting, indicate the feasibility of early COVID-19 screening and that non-COVID infiltration is the group of patients most similar to COVID-19 in terms of radiological description of X-ray. Therefore, an efficient COVID-19 screening should be complemented with other clinical data to better discriminate these cases.
	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; 600.139; 600.145; 601.337			Approved	no
	Call Number	Admin @ si @ GDS2020			Serial	3474
Permanent link to this record



	Author	Oriol Ramos Terrades; Albert Berenguel; Debora Gil
	Title	A flexible outlier detector based on a topology given by graph communities			Type	Miscellaneous
	Year	2020	Publication	Arxiv	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Outlier, or anomaly, detection is essential for optimal performance of machine learning methods and statistical predictive models. It is not just a technical step in a data cleaning process but a key topic in many fields such as fraudulent document detection, in medical applications and assisted diagnosis systems or detecting security threats. In contrast to population-based methods, neighborhood based local approaches are simple flexible methods that have the potential to perform well in small sample size unbalanced problems. However, a main concern of local approaches is the impact that the computation of each sample neighborhood has on the method performance. Most approaches use a distance in the feature space to define a single neighborhood that requires careful selection of several parameters. This work presents a local approach based on a local measure of the heterogeneity of sample labels in the feature space considered as a topological manifold. Topology is computed using the communities of a weighted graph codifying mutual nearest neighbors in the feature space. This way, we provide with a set of multiple neighborhoods able to describe the structure of complex spaces without parameter fine tuning. The extensive experiments on real-world data sets show that our approach overall outperforms, both, local and global strategies in multi and single view settings.
	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; DAG; 600.139; 600.145; 600.140; 600.121			Approved	no
	Call Number	Admin @ si @ RBG2020			Serial	3475
Permanent link to this record



	Author	Diego Porres
	Title	Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks			Type	Conference Article
	Year	2021	Publication	Machine Learning for Creativity and Design, Neurips Workshop	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Generative Adversarial Networks have long since revolutionized the world of computer vision and, tied to it, the world of art. Arduous efforts have gone into fully utilizing and stabilizing training so that outputs of the Generator network have the highest possible fidelity, but little has gone into using the Discriminator after training is complete. In this work, we propose to use the latter and show a way to use the features it has learned from the training dataset to both alter an image and generate one from scratch. We name this method Discriminator Dreaming, and the full code can be found at this https URL.
	Address	Virtual; December 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	NEURIPSW
	Notes	ADAS; 601.365			Approved	no
	Call Number	Admin @ si @ Por2021			Serial	3597
Permanent link to this record



	Author	Gabriel Villalonga
	Title	Leveraging Synthetic Data to Create Autonomous Driving Perception Systems			Type	Book Whole
	Year	2021	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Manually annotating images to develop vision models has been a major bottleneck since computer vision and machine learning started to walk together. This has been more evident since computer vision falls on the shoulders of data-hungry deep learning techniques. When addressing on-board perception for autonomous driving, the curse of data annotation is exacerbated due to the use of additional sensors such as LiDAR. Therefore, any approach aiming at reducing such a timeconsuming and costly work is of high interest for addressing autonomous driving and, in fact, for any application requiring some sort of artificial perception. In the last decade, it has been shown that leveraging from synthetic data is a paradigm worth to pursue in order to minimizing manual data annotation. The reason is that the automatic process of generating synthetic data can also produce different types of associated annotations (e.g. object bounding boxes for synthetic images and LiDAR pointclouds, pixel/point-wise semantic information, etc.). Directly using synthetic data for training deep perception models may not be the definitive solution in all circumstances since it can appear a synth-to-real domain shift. In this context, this work focuses on leveraging synthetic data to alleviate manual annotation for three perception tasks related to driving assistance and autonomous driving. In all cases, we assume the use of deep convolutional neural networks (CNNs) to develop our perception models. The first task addresses traffic sign recognition (TSR), a kind of multi-class classification problem. We assume that the number of sign classes to be recognized must be suddenly increased without having annotated samples to perform the corresponding TSR CNN re-training. We show that leveraging synthetic samples of such new classes and transforming them by a generative adversarial network (GAN) trained on the known classes (i.e. without using samples from the new classes), it is possible to re-train the TSR CNN to properly classify all the signs for a ∼ 1/4 ratio of new/known sign classes. The second task addresses on-board 2D object detection, focusing on vehicles and pedestrians. In this case, we assume that we receive a set of images without the annotations required to train an object detector, i.e. without object bounding boxes. Therefore, our goal is to self-annotate these images so that they can later be used to train the desired object detector. In order to reach this goal, we leverage from synthetic data and propose a semi-supervised learning approach based on the co-training idea. In fact, we use a GAN to reduce the synthto-real domain shift before applying co-training. Our quantitative results show that co-training and GAN-based image-to-image translation complement each other up to allow the training of object detectors without manual annotation, and still almost reaching the upper-bound performances of the detectors trained from human annotations. While in previous tasks we focus on vision-based perception, the third task we address focuses on LiDAR pointclouds. Our initial goal was to develop a 3D object detector trained on synthetic LiDAR-style pointclouds. While for images we may expect synth/real-to-real domain shift due to differences in their appearance (e.g. when source and target images come from different camera sensors), we did not expect so for LiDAR pointclouds since these active sensors factor out appearance and provide sampled shapes. However, in practice, we have seen that it can be domain shift even among real-world LiDAR pointclouds. Factors such as the sampling parameters of the LiDARs, the sensor suite configuration onboard the ego-vehicle, and the human annotation of 3D bounding boxes, do induce a domain shift. We show it through comprehensive experiments with different publicly available datasets and 3D detectors. This redirected our goal towards the design of a GAN for pointcloud-to-pointcloud translation, a relatively unexplored topic. Finally, it is worth to mention that all the synthetic datasets used for these three tasks, have been designed and generated in the context of this PhD work and will be publicly released. Overall, we think this PhD presents several steps forward to encourage leveraging synthetic data for developing deep perception models in the field of driving assistance and autonomous driving.
	Address	February 2021
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	Ediciones Graficas Rey	Place of Publication		Editor	Antonio Lopez;German Ros
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-122714-2-3	Medium
	Area		Expedition		Conference
	Notes	ADAS; 600.118			Approved	no
	Call Number	Admin @ si @ Vil2021			Serial	3599
Permanent link to this record



	Author	Pau Riba
	Title	Distilling Structure from Imagery: Graph-based Models for the Interpretation of Document Images			Type	Book Whole
	Year	2020	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	From its early stages, the community of Pattern Recognition and Computer Vision has considered the importance of leveraging the structural information when understanding images. Usually, graphs have been proposed as a suitable model to represent this kind of information due to their flexibility and representational power able to codify both, the components, objects, or entities and their pairwise relationship. Even though graphs have been successfully applied to a huge variety of tasks, as a result of their symbolic and relational nature, graphs have always suffered from some limitations compared to statistical approaches. Indeed, some trivial mathematical operations do not have an equivalence in the graph domain. For instance, in the core of many pattern recognition applications, there is a need to compare two objects. This operation, which is trivial when considering feature vectors defined in \(\mathbb{R}^n\), is not properly defined for graphs. In this thesis, we have investigated the importance of the structural information from two perspectives, the traditional graph-based methods and the new advances on Geometric Deep Learning. On the one hand, we explore the problem of defining a graph representation and how to deal with it on a large scale and noisy scenario. On the other hand, Graph Neural Networks are proposed to first redefine a Graph Edit Distance methodologies as a metric learning problem, and second, to apply them in a real use case scenario for the detection of repetitive patterns which define tables in invoice documents. As experimental framework, we have validated the different methodological contributions in the domain of Document Image Analysis and Recognition.
	Address
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	Ediciones Graficas Rey	Place of Publication		Editor	Josep Llados;Alicia Fornes
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-121011-6-4	Medium
	Area		Expedition		Conference
	Notes	DAG; 600.121			Approved	no
	Call Number	Admin @ si @ Rib20			Serial	3478
Permanent link to this record



	Author	Raul Gomez
	Title	Exploiting the Interplay between Visual and Textual Data for Scene Interpretation			Type	Book Whole
	Year	2020	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Machine learning experimentation under controlled scenarios and standard datasets is necessary to compare algorithms performance by evaluating all of them in the same setup. However, experimentation on how those algorithms perform on unconstrained data and applied tasks to solve real world problems is also a must to ascertain how that research can contribute to our society. In this dissertation we experiment with the latest computer vision and natural language processing algorithms applying them to multimodal scene interpretation. Particularly, we research on how image and text understanding can be jointly exploited to address real world problems, focusing on learning from Social Media data. We address several tasks that involve image and textual information, discuss their characteristics and offer our experimentation conclusions. First, we work on detection of scene text in images. Then, we work with Social Media posts, exploiting the captions associated to images as supervision to learn visual features, which we apply to multimodal semantic image retrieval. Subsequently, we work with geolocated Social Media images with associated tags, experimenting on how to use the tags as supervision, on location sensitive image retrieval and on exploiting location information for image tagging. Finally, we work on a specific classification problem of Social Media publications consisting on an image and a text: Multimodal hate speech classification.
	Address
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	Ediciones Graficas Rey	Place of Publication		Editor	Dimosthenis Karatzas;Lluis Gomez;Jaume Gibert
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-121011-7-1	Medium
	Area		Expedition		Conference
	Notes	DAG; 600.121			Approved	no
	Call Number	Admin @ si @ Gom20			Serial	3479
Permanent link to this record



	Author	Sounak Dey
	Title	Mapping between Images and Conceptual Spaces: Sketch-based Image Retrieval			Type	Book Whole
	Year	2020	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	This thesis presents several contributions to the literature of sketch based image retrieval (SBIR). In SBIR the first challenge we face is how to map two different domains to common space for effective retrieval of images, while tackling the different levels of abstraction people use to express their notion of objects around while sketching. To this extent we first propose a cross-modal learning framework that maps both sketches and text into a joint embedding space invariant to depictive style, while preserving semantics. Then we have also investigated different query types possible to encompass people's dilema in sketching certain world objects. For this we propose an approach for multi-modal image retrieval in multi-labelled images. A multi-modal deep network architecture is formulated to jointly model sketches and text as input query modalities into a common embedding space, which is then further aligned with the image feature space. This permits encoding the object-based features and its alignment with the query irrespective of the availability of the co-occurrence of different objects in the training set. Finally, we explore the problem of zero-shot sketch-based image retrieval (ZS-SBIR), where human sketches are used as queries to conduct retrieval of photos from unseen categories. We importantly advance prior arts by proposing a novel ZS-SBIR scenario that represents a firm step forward in its practical application. The new setting uniquely recognises two important yet often neglected challenges of practical ZS-SBIR, (i) the large domain gap between amateur sketch and photo, and (ii) the necessity for moving towards large-scale retrieval. We first contribute to the community a novel ZS-SBIR dataset, QuickDraw-Extended. We also in this dissertation pave the path to the future direction of research in this domain.
	Address
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	Ediciones Graficas Rey	Place of Publication		Editor	Josep Llados;Umapada Pal
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-121011-8-8	Medium
	Area		Expedition		Conference
	Notes	DAG; 600.121			Approved	no
	Call Number	Admin @ si @ Dey20			Serial	3480
Permanent link to this record



	Author	Marc Masana
	Title	Lifelong Learning of Neural Networks: Detecting Novelty and Adapting to New Domains without Forgetting			Type	Book Whole
	Year	2020	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Computer vision has gone through considerable changes in the last decade as neural networks have come into common use. As available computational capabilities have grown, neural networks have achieved breakthroughs in many computer vision tasks, and have even surpassed human performance in others. With accuracy being so high, focus has shifted to other issues and challenges. One research direction that saw a notable increase in interest is on lifelong learning systems. Such systems should be capable of efficiently performing tasks, identifying and learning new ones, and should moreover be able to deploy smaller versions of themselves which are experts on specific tasks. In this thesis, we contribute to research on lifelong learning and address the compression and adaptation of networks to small target domains, the incremental learning of networks faced with a variety of tasks, and finally the detection of out-of-distribution samples at inference time. We explore how knowledge can be transferred from large pretrained models to more task-specific networks capable of running on smaller devices by extracting the most relevant information. Using a pretrained model provides more robust representations and a more stable initialization when learning a smaller task, which leads to higher performance and is known as domain adaptation. However, those models are too large for certain applications that need to be deployed on devices with limited memory and computational capacity. In this thesis we show that, after performing domain adaptation, some learned activations barely contribute to the predictions of the model. Therefore, we propose to apply network compression based on low-rank matrix decomposition using the activation statistics. This results in a significant reduction of the model size and the computational cost. Like human intelligence, machine intelligence aims to have the ability to learn and remember knowledge. However, when a trained neural network is presented with learning a new task, it ends up forgetting previous ones. This is known as catastrophic forgetting and its avoidance is studied in continual learning. The work presented in this thesis extensively surveys continual learning techniques and presents an approach to avoid catastrophic forgetting in sequential task learning scenarios. Our technique is based on using ternary masks in order to update a network to new tasks, reusing the knowledge of previous ones while not forgetting anything about them. In contrast to earlier work, our masks are applied to the activations of each layer instead of the weights. This considerably reduces the number of parameters to be added for each new task. Furthermore, the analysis on a wide range of work on incremental learning without access to the task-ID, provides insight on current state-of-the-art approaches that focus on avoiding catastrophic forgetting by using regularization, rehearsal of previous tasks from a small memory, or compensating the task-recency bias. Neural networks trained with a cross-entropy loss force the outputs of the model to tend toward a one-hot encoded vector. This leads to models being too overly confident when presented with images or classes that were not present in the training distribution. The capacity of a system to be aware of the boundaries of the learned tasks and identify anomalies or classes which have not been learned yet is key to lifelong learning and autonomous systems. In this thesis, we present a metric learning approach to out-of-distribution detection that learns the task at hand on an embedding space.
	Address
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	Ediciones Graficas Rey	Place of Publication		Editor	Joost Van de Weijer;Andrew Bagdanov
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-121011-9-5	Medium
	Area		Expedition		Conference
	Notes	LAMP; 600.120			Approved	no
	Call Number	Admin @ si @ Mas20			Serial	3481
Permanent link to this record