Home << 1 2 3 4 5 6 7 8 9 >>
List View
 | 
Citations
 | 
Details
   web
Records
Author Debora Gil; Oriol Ramos Terrades; Raquel Perez
Title Topological Radiomics (TOPiomics): Early Detection of Genetic Abnormalities in Cancer Treatment Evolution Type Book Chapter
Year 2021 Publication Extended Abstracts GEOMVAP 2019, Trends in Mathematics 15 Abbreviated Journal
Volume 15 Issue Pages 89–93
Keywords
Abstract Abnormalities in radiomic measures correlate to genomic alterations prone to alter the outcome of personalized anti-cancer treatments. TOPiomics is a new method for the early detection of variations in tumor imaging phenotype from a topological structure in multi-view radiomic spaces.
Address
Corporate Author Thesis
Publisher Springer Nature Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes IAM; DAG; 600.120; 600.145; 600.139 Approved no
Call Number Admin @ si @ GRP2021 Serial 3594
Permanent link to this record
 
 
Author David Aldavert
Title Efficient and Scalable Handwritten Word Spotting on Historical Documents using Bag of Visual Words Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Word spotting can be defined as the pattern recognition tasked aimed at locating and retrieving a specific keyword within a document image collection without explicitly transcribing the whole corpus. Its use is particularly interesting when applied in scenarios where Optical Character Recognition performs poorly or can not be used at all. This thesis focuses on such a scenario, word spotting on historical handwritten documents that have been written by a single author or by multiple authors with a similar calligraphy.
This problem requires a visual signature that is robust to image artifacts, flexible to accommodate script variations and efficient to retrieve information in a rapid manner. For this, we have developed a set of word spotting methods that on their foundation use the well known Bag-of-Visual-Words (BoVW) representation. This representation has gained popularity among the document image analysis community to characterize handwritten words
in an unsupervised manner. However, most approaches on this field rely on a basic BoVW configuration and disregard complex encoding and spatial representations. We determine which BoVW configurations provide the best performance boost to a spotting system.
Then, we extend the segmentation-based word spotting, where word candidates are given a priori, to segmentation-free spotting. The proposed approach seeds the document images with overlapping word location candidates and characterizes them with a BoVW signature. Retrieval is achieved comparing the query and candidate signatures and returning the locations that provide a higher consensus. This is a simple but powerful approach that requires a more compact signature than in a segmentation-based scenario. We first
project the BoVW signature into a reduced semantic topics space and then compress it further using Product Quantizers. The resulting signature only requires a few dozen bytes, allowing us to index thousands of pages on a common desktop computer. The final system still yields a performance comparable to the state-of-the-art despite all the information loss during the compression phases.
Afterwards, we also study how to combine different modalities of information in order to create a query-by-X spotting system where, words are indexed using an information modality and queries are retrieved using another. We consider three different information modalities: visual, textual and audio. Our proposal is to create a latent feature space where features which are semantically related are projected onto the same topics. Creating thus a new feature space where information from different modalities can be compared. Later, we consider the codebook generation and descriptor encoding problem. The codebooks used to encode the BoVW signatures are usually created using an unsupervised clustering algorithm and, they require to test multiple parameters to determine which configuration is best for a certain document collection. We propose a semantic clustering algorithm which allows to estimate the best parameter from data. Since gather annotated data is costly, we use synthetically generated word images. The resulting codebook is database agnostic, i. e. a codebook that yields a good performance on document collections that use the same script. We also propose the use of an additional codebook to approximate descriptors and reduce the descriptor encoding
complexity to sub-linear.
Finally, we focus on the problem of signatures dimensionality. We propose a new symbol probability signature where each bin represents the probability that a certain symbol is present a certain location of the word image. This signature is extremely compact and combined with compression techniques can represent word images with just a few bytes per signature.
Address April 2021
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Marçal Rusiñol;Josep Llados
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-122714-5-4 Medium
Area Expedition Conference
Notes DAG; 600.121 Approved no
Call Number Admin @ si @ Ald2021 Serial 3601
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 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 Minesh Mathew; Dimosthenis Karatzas; C.V. Jawahar
Title DocVQA: A Dataset for VQA on Document Images Type Conference Article
Year 2021 Publication IEEE Winter Conference on Applications of Computer Vision Abbreviated Journal
Volume Issue Pages 2200-2209
Keywords
Abstract We present a new dataset for Visual Question Answering (VQA) on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+ document images. Detailed analysis of the dataset in comparison with similar datasets for VQA and reading comprehension is presented. We report several baseline results by adopting existing VQA and reading comprehension models. Although the existing models perform reasonably well on certain types of questions, there is large performance gap compared to human performance (94.36% accuracy). The models need to improve specifically on questions where understanding structure of the document is crucial. The dataset, code and leaderboard are available at docvqa. org
Address Virtual; January 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 WACV
Notes DAG; 600.121 Approved no
Call Number Admin @ si @ MKJ2021 Serial 3498
Permanent link to this record
 
 
Author Gemma Rotger
Title Lifelike Humans: Detailed Reconstruction of Expressive Human Faces Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Developing human-like digital characters is a challenging task since humans are used to recognizing our fellows, and find the computed generated characters inadequately humanized. To fulfill the standards of the videogame and digital film productions it is necessary to model and animate these characters the most closely to human beings. However, it is an arduous and expensive task, since many artists and specialists are required to work on a single character. Therefore, to fulfill these requirements we found an interesting option to study the automatic creation of detailed characters through inexpensive setups. In this work, we develop novel techniques to bring detailed characters by combining different aspects that stand out when developing realistic characters, skin detail, facial hairs, expressions, and microexpressions. We examine each of the mentioned areas with the aim of automatically recover each of the parts without user interaction nor training data. We study the problems for their robustness but also for the simplicity of the setup, preferring single-image with uncontrolled illumination and methods that can be easily computed with the commodity of a standard laptop. A detailed face with wrinkles and skin details is vital to develop a realistic character. In this work, we introduce our method to automatically describe facial wrinkles on the image and transfer to the recovered base face. Then we advance to facial hair recovery by resolving a fitting problem with a novel parametrization model. As of last, we develop a mapping function that allows transfer expressions and microexpressions between different meshes, which provides realistic animations to our detailed mesh. We cover all the mentioned points with the focus on key aspects as (i) how to describe skin wrinkles in a simple and straightforward manner, (ii) how to recover 3D from 2D detections, (iii) how to recover and model facial hair from 2D to 3D, (iv) how to transfer expressions between models holding both skin detail and facial hair, (v) how to perform all the described actions without training data nor user interaction. In this work, we present our proposals to solve these aspects with an efficient and simple setup. We validate our work with several datasets both synthetic and real data, prooving remarkable results even in challenging cases as occlusions as glasses, thick beards, and indeed working with different face topologies like single-eyed cyclops.
Address
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Felipe Lumbreras;Antonio Agudo
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-122714-3-0 Medium
Area Expedition Conference
Notes ADAS Approved no
Call Number Admin @ si @ Rot2021 Serial 3513
Permanent link to this record
 
 
Author Carola Figueroa Flores; Bogdan Raducanu; David Berga; Joost Van de Weijer
Title Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains Type Conference Article
Year 2021 Publication 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications Abbreviated Journal
Volume 4 Issue Pages 163-171
Keywords
Abstract arXiv:2007.12562
Most of the saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline, like for instance, image classification. In the current paper, we propose an approach which does not require explicit saliency maps to improve image classification, but they are learned implicitely, during the training of an end-to-end image classification task. We show that our approach obtains similar results as the case when the saliency maps are provided explicitely. Combining RGB data with saliency maps represents a significant advantage for object recognition, especially for the case when training data is limited. We validate our method on several datasets for fine-grained classification tasks (Flowers, Birds and Cars). In addition, we show that our saliency estimation method, which is trained without any saliency groundtruth data, obtains competitive results on real image saliency benchmark (Toronto), and outperforms deep saliency models with synthetic images (SID4VAM).
Address Virtual; February 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 VISAPP
Notes LAMP Approved no
Call Number Admin @ si @ FRB2021c Serial 3540
Permanent link to this record
 
 
Author Idoia Ruiz; Lorenzo Porzi; Samuel Rota Bulo; Peter Kontschieder; Joan Serrat
Title Weakly Supervised Multi-Object Tracking and Segmentation Type Conference Article
Year 2021 Publication IEEE Winter Conference on Applications of Computer Vision Workshops Abbreviated Journal
Volume Issue Pages 125-133
Keywords
Abstract We introduce the problem of weakly supervised MultiObject Tracking and Segmentation, i.e. joint weakly supervised instance segmentation and multi-object tracking, in which we do not provide any kind of mask annotation.
To address it, we design a novel synergistic training strategy by taking advantage of multi-task learning, i.e. classification and tracking tasks guide the training of the unsupervised instance segmentation. For that purpose, we extract weak foreground localization information, provided by
Grad-CAM heatmaps, to generate a partial ground truth to learn from. Additionally, RGB image level information is employed to refine the mask prediction at the edges of the
objects. We evaluate our method on KITTI MOTS, the most representative benchmark for this task, reducing the performance gap on the MOTSP metric between the fully supervised and weakly supervised approach to just 12% and 12.7 % for cars and pedestrians, respectively.
Address Virtual; January 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 WACVW
Notes ADAS; 600.118; 600.124 Approved no
Call Number Admin @ si @ RPR2021 Serial 3548
Permanent link to this record
 
 
Author Ozge Mercanoglu Sincan; Julio C. S. Jacques Junior; Sergio Escalera; Hacer Yalim Keles
Title ChaLearn LAP Large Scale Signer Independent Isolated Sign Language Recognition Challenge: Design, Results and Future Research Type Conference Article
Year 2021 Publication Conference on Computer Vision and Pattern Recognition Workshops Abbreviated Journal
Volume Issue Pages 3467-3476
Keywords
Abstract The performances of Sign Language Recognition (SLR) systems have improved considerably in recent years. However, several open challenges still need to be solved to allow SLR to be useful in practice. The research in the field is in its infancy in regards to the robustness of the models to a large diversity of signs and signers, and to fairness of the models to performers from different demographics. This work summarises the ChaLearn LAP Large Scale Signer Independent Isolated SLR Challenge, organised at CVPR 2021 with the goal of overcoming some of the aforementioned challenges. We analyse and discuss the challenge design, top winning solutions and suggestions for future research. The challenge attracted 132 participants in the RGB track and 59 in the RGB+Depth track, receiving more than 1.5K submissions in total. Participants were evaluated using a new large-scale multi-modal Turkish Sign Language (AUTSL) dataset, consisting of 226 sign labels and 36,302 isolated sign video samples performed by 43 different signers. Winning teams achieved more than 96% recognition rate, and their approaches benefited from pose/hand/face estimation, transfer learning, external data, fusion/ensemble of modalities and different strategies to model spatio-temporal information. However, methods still fail to distinguish among very similar signs, in particular those sharing similar hand trajectories.
Address Virtual; June 2021
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference CVPRW
Notes HuPBA; no proj Approved no
Call Number Admin @ si @ MJE2021 Serial 3560
Permanent link to this record
 
 
Author Albin Soutif; Marc Masana; Joost Van de Weijer; Bartlomiej Twardowski
Title On the importance of cross-task features for class-incremental learning Type Conference Article
Year 2021 Publication Theory and Foundation of continual learning workshop of ICML Abbreviated Journal
Volume Issue Pages
Keywords
Abstract In class-incremental learning, an agent with limited resources needs to learn a sequence of classification tasks, forming an ever growing classification problem, with the constraint of not being able to access data from previous tasks. The main difference with task-incremental learning, where a task-ID is available at inference time, is that the learner also needs to perform crosstask discrimination, i.e. distinguish between classes that have not been seen together. Approaches to tackle this problem are numerous and mostly make use of an external memory (buffer) of non-negligible size. In this paper, we ablate the learning of crosstask features and study its influence on the performance of basic replay strategies used for class-IL. We also define a new forgetting measure for class-incremental learning, and see that forgetting is not the principal cause of low performance. Our experimental results show that future algorithms for class-incremental learning should not only prevent forgetting, but also aim to improve the quality of the cross-task features. This is especially important when the number of classes per task is small.
Address Virtual; July 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 ICMLW
Notes LAMP Approved no
Call Number Admin @ si @ SMW2021 Serial 3588
Permanent link to this record
 
 
Author Hassan Ahmed Sial
Title Estimating Light Effects from a Single Image: Deep Architectures and Ground-Truth Generation Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract In this thesis, we explore how to estimate the effects of the light interacting with the scene objects from a single image. To achieve this goal, we focus on recovering intrinsic components like reflectance, shading, or light properties such as color and position using deep architectures. The success of these approaches relies on training on large and diversified image datasets. Therefore, we present several contributions on this such as: (a) a data-augmentation technique; (b) a ground-truth for an existing multi-illuminant dataset; (c) a family of synthetic datasets, SID for Surreal Intrinsic Datasets, with diversified backgrounds and coherent light conditions; and (d) a practical pipeline to create hybrid ground-truths to overcome the complexity of acquiring realistic light conditions in a massive way. In parallel with the creation of datasets, we trained different flexible encoder-decoder deep architectures incorporating physical constraints from the image formation models.

In the last part of the thesis, we apply all the previous experience to two different problems. Firstly, we create a large hybrid Doc3DShade dataset with real shading and synthetic reflectance under complex illumination conditions, that is used to train a two-stage architecture that improves the character recognition task in complex lighting conditions of unwrapped documents. Secondly, we tackle the problem of single image scene relighting by extending both, the SID dataset to present stronger shading and shadows effects, and the deep architectures to use intrinsic components to estimate new relit images.
Address September 2021
Corporate Author Thesis Ph.D. thesis
Publisher IMPRIMA Place of Publication Editor Maria Vanrell;Ramon Baldrich
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-122714-8-5 Medium
Area Expedition Conference
Notes CIC; Approved no
Call Number Admin @ si @ Sia2021 Serial 3607
Permanent link to this record
 
 
Author Fei Yang
Title Towards Practical Neural Image Compression Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Images and videos are pervasive in our life and communication. With advances in smart and portable devices, high capacity communication networks and high definition cinema, image and video compression are more relevant than ever. Traditional block-based linear transform codecs such as JPEG, H.264/AVC or the recent H.266/VVC are carefully designed to meet not only the rate-distortion criteria, but also the practical requirements of applications.
Recently, a new paradigm based on deep neural networks (i.e., neural image/video compression) has become increasingly popular due to its ability to learn powerful nonlinear transforms and other coding tools directly from data instead of being crafted by humans, as was usual in previous coding formats. While achieving excellent rate-distortion performance, these approaches are still limited mostly to research environments due to heavy models and other practical limitations, such as being limited to function on a particular rate and due to high memory and computational cost. In this thesis, we study these practical limitations, and designing more practical neural image compression approaches.
After analyzing the differences between traditional and neural image compression, our first contribution is the modulated autoencoder (MAE), a framework that includes a mechanism to provide multiple rate-distortion options within a single model with comparable performance to independent models. In a second contribution, we propose the slimmable compressive autoencoder (SlimCAE), which in addition to variable rate, can optimize the complexity of the model and thus reduce significantly the memory and computational burden.
Modern generative models can learn custom image transformation directly from suitable datasets following encoder-decoder architectures, task known as image-to-image (I2I) translation. Building on our previous work, we study the problem of distributed I2I translation, where the latent representation is transmitted through a binary channel and decoded in a remote receiving side. We also propose a variant that can perform both translation and the usual autoencoding functionality.
Finally, we also consider neural video compression, where the autoencoder is typically augmented with temporal prediction via motion compensation. One of the main bottlenecks of that framework is the optical flow module that estimates the displacement to predict the next frame. Focusing on this module, we propose a method that improves the accuracy of the optical flow estimation and a simplified variant that reduces the computational cost.
Key words: neural image compression, neural video compression, optical flow, practical neural image compression, compressive autoencoders, image-to-image translation, deep learning.
Address December 2021
Corporate Author Thesis Ph.D. thesis
Publisher IMPRIMA Place of Publication Editor Luis Herranz;Mikhail Mozerov;Yongmei Cheng
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-122714-7-8 Medium
Area Expedition Conference
Notes LAMP Approved no
Call Number Admin @ si @ Yan2021 Serial 3608
Permanent link to this record
 
 
Author Javad Zolfaghari Bengar
Title Reducing Label Effort with Deep Active Learning Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Deep convolutional neural networks (CNNs) have achieved superior performance in many visual recognition applications, such as image classification, detection and segmentation. Training deep CNNs requires huge amounts of labeled data, which is expensive and labor intensive to collect. Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected
informative and/or representative samples. In this thesis we study several aspects of active learning including video object detection for autonomous driving systems, image classification on balanced and imbalanced datasets and the incorporation of self-supervised learning in active learning. We briefly describe our approach in each of these areas to reduce the labeling effort.
In chapter two we introduce a novel active learning approach for object detection in videos by exploiting temporal coherence. Our criterion is based on the estimated number of errors in terms of false positives and false negatives. Additionally, we introduce a synthetic video dataset, called SYNTHIA-AL, specially designed to evaluate active
learning for video object detection in road scenes. Finally, we show that our
approach outperforms active learning baselines tested on two outdoor datasets.
In the next chapter we address the well-known problem of over confidence in the neural networks. As an alternative to network confidence, we propose a new informativeness-based active learning method that captures the learning dynamics of neural network with a metric called label-dispersion. This metric is low when the network consistently assigns the same label to the sample during the course of training and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results.
In chapter four, we tackle the problem of sampling bias in active learning methods on imbalanced datasets. Active learning is generally studied on balanced datasets where an equal amount of images per class is available. However, real-world datasets suffer from severe imbalanced classes, the so called longtail distribution. We argue that this further complicates the active learning process, since the imbalanced data pool can result in suboptimal classifiers. To address this problem in the context of active learning, we propose a general optimization framework that explicitly takes class-balancing into account. Results on three datasets show that the method is general (it can be combined with most existing active learning algorithms) and can be effectively applied to boost the performance of both informative and representative-based active learning methods. In addition, we show that also on balanced datasets our method generally results in a performance gain.
Another paradigm to reduce the annotation effort is self-training that learns from a large amount of unlabeled data in an unsupervised way and fine-tunes on few labeled samples. Recent advancements in self-training have achieved very impressive results rivaling supervised learning on some datasets. In the last chapter we focus on whether active learning and self supervised learning can benefit from each other.
We study object recognition datasets with several labeling budgets for the evaluations. Our experiments reveal that self-training is remarkably more efficient than active learning at reducing the labeling effort, that for a low labeling budget, active learning offers no benefit to self-training, and finally that the combination of active learning and self-training is fruitful when the labeling budget is high.
Address December 2021
Corporate Author Thesis Ph.D. thesis
Publisher IMPRIMA Place of Publication Editor Joost Van de Weijer;Bogdan Raducanu
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-122714-9-2 Medium
Area Expedition Conference
Notes LAMP; Approved no
Call Number Admin @ si @ Zol2021 Serial 3609
Permanent link to this record
 
 
Author Edgar Riba
Title Geometric Computer Vision Techniques for Scene Reconstruction Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract From the early stages of Computer Vision, scene reconstruction has been one of the most studied topics leading to a wide variety of new discoveries and applications. Object grasping and manipulation, localization and mapping, or even visual effect generation are different examples of applications in which scene reconstruction has taken an important role for industries such as robotics, factory automation, or audio visual production. However, scene reconstruction is an extensive topic that can be approached in many different ways with already existing solutions that effectively work in controlled environments. Formally, the problem of scene reconstruction can be formulated as a sequence of independent processes which compose a pipeline. In this thesis, we analyse some parts of the reconstruction pipeline from which we contribute with novel methods using Convolutional Neural Networks (CNN) proposing innovative solutions that consider the optimisation of the methods in an end-to-end fashion. First, we review the state of the art of classical local features detectors and descriptors and contribute with two novel methods that inherently improve pre-existing solutions in the scene reconstruction pipeline.

It is a fact that computer science and software engineering are two fields that usually go hand in hand and evolve according to mutual needs making easier the design of complex and efficient algorithms. For this reason, we contribute with Kornia, a library specifically designed to work with classical computer vision techniques along with deep neural networks. In essence, we created a framework that eases the design of complex pipelines for computer vision algorithms so that can be included within neural networks and be used to backpropagate gradients throw a common optimisation framework. Finally, in the last chapter of this thesis we develop the aforementioned concept of designing end-to-end systems with classical projective geometry. Thus, we contribute with a solution to the problem of synthetic view generation by hallucinating novel views from high deformable cloths objects using a geometry aware end-to-end system. To summarize, in this thesis we demonstrate that with a proper design that combine classical geometric computer vision methods with deep learning techniques can lead to improve pre-existing solutions for the problem of scene reconstruction.
Address February 2021
Corporate Author Thesis Ph.D. thesis
Publisher Place of Publication Editor Daniel Ponsa
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 Approved no
Call Number Admin @ si @ Rib2021 Serial 3610
Permanent link to this record
 
 
Author Pau Torras; Arnau Baro; Lei Kang; Alicia Fornes
Title On the Integration of Language Models into Sequence to Sequence Architectures for Handwritten Music Recognition Type Conference Article
Year 2021 Publication International Society for Music Information Retrieval Conference Abbreviated Journal
Volume Issue Pages 690-696
Keywords
Abstract Despite the latest advances in Deep Learning, the recognition of handwritten music scores is still a challenging endeavour. Even though the recent Sequence to Sequence(Seq2Seq) architectures have demonstrated its capacity to reliably recognise handwritten text, their performance is still far from satisfactory when applied to historical handwritten scores. Indeed, the ambiguous nature of handwriting, the non-standard musical notation employed by composers of the time and the decaying state of old paper make these scores remarkably difficult to read, sometimes even by trained humans. Thus, in this work we explore the incorporation of language models into a Seq2Seq-based architecture to try to improve transcriptions where the aforementioned unclear writing produces statistically unsound mistakes, which as far as we know, has never been attempted for this field of research on this architecture. After studying various Language Model integration techniques, the experimental evaluation on historical handwritten music scores shows a significant improvement over the state of the art, showing that this is a promising research direction for dealing with such difficult manuscripts.
Address Virtual; November 2021
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ISMIR
Notes DAG; 600.140; 600.121 Approved no
Call Number Admin @ si @ TBK2021 Serial 3616
Permanent link to this record