Home [71–80] << 81 82 83 84 85 86 87 88 89 90 >> [91–100]
List View
 | 
Citations
 | 
Details
   web
Records
Author Enric Marti; Debora Gil; Carme Julia
Title A PBL experience in the teaching of Computer Graphics Type Conference Article
Year 2005 Publication EUROGRAPHICS Proceedings Abbreviated Journal
Volume 5 Issue 1 Pages 95-103
Keywords project-based learning; computer graphics education; Open GL; rendering techniques; computer animation techniques; Graphics packages; Hierarchy and geometric transformations; Animation; Color; shading; shadowing and texture; fractals; hidden line/surface removal; Problem Based Learning
Abstract Project-Based Learning (PBL) is an educational strategy to improve student’s learning capability that, in recent years, has had a progressive acceptance in undergraduate studies. This methodology is based on solving a problem or project in a student working group. In this way, PBL focuses on learning the necessary tools to correctly find a solution to given problems. Since the learning initiative is transferred to the student, the PBL method promotes students own abilities. This allows a better assessment of the true workload that carries out the student in the subject. It follows that the methodology conforms to the guidelines of the Bologna document, which quantifies the student workload in a subject by means of the European credit transfer system (ECTS). PBL is currently applied in undergraduate studies needing strong practical training such as medicine, nursing or law sciences. Although this is also the case in engineering studies, amazingly, few experiences have been reported. In this paper we propose to use PBL in the educational organization of the Computer Graphics subjects in the Computer Science degree. Our PBL project focuses in the development of a C++ graphical environment based on the OpenGL libraries for visualization and handling of different graphical objects. The starting point is a basic skeleton that already includes lighting functions, perspective projection with mouse interaction to change the point of view and three predefined objects. Students have to complete this skeleton by adding their own functions to solve the project. A total number of 10 projects have been proposed and successfully solved. The exercises range from human face rendering to articulated objects, such as robot arms or puppets. In the present paper we extensively report the statement and educational objectives for two of the projects: solar system visualization and a chess game. We report our earlier educational experience based on the standard classroom theoretical, problem and practice sessions and the reasons that motivated searching for other learning methods. We have mainly chosen PBL because it improves the student learning initiative. We have applied the PBL educational model since the beginning of the second semester. The student’s feedback increases in his interest for the subject. We present a comparative study of the teachers’ and students’ workload between PBL and the classic teaching approach, which suggests that the workload increase in PBL is not as high as it seems.
Address (down) Dublin; Ireland; September 2005
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 EUROGRAPHICS
Notes IAM;ADAS; Approved no
Call Number IAM @ iam @ MGJ2005 Serial 1593
Permanent link to this record
 
 
Author Marçal Rusiñol; David Aldavert; Dimosthenis Karatzas; Ricardo Toledo; Josep Llados
Title Interactive Trademark Image Retrieval by Fusing Semantic and Visual Content. Advances in Information Retrieval Type Conference Article
Year 2011 Publication 33rd European Conference on Information Retrieval Abbreviated Journal
Volume 6611 Issue Pages 314-325
Keywords
Abstract In this paper we propose an efficient queried-by-example retrieval system which is able to retrieve trademark images by similarity from patent and trademark offices' digital libraries. Logo images are described by both their semantic content, by means of the Vienna codes, and their visual contents, by using shape and color as visual cues. The trademark descriptors are then indexed by a locality-sensitive hashing data structure aiming to perform approximate k-NN search in high dimensional spaces in sub-linear time. The resulting ranked lists are combined by using the Condorcet method and a relevance feedback step helps to iteratively revise the query and refine the obtained results. The experiments demonstrate the effectiveness and efficiency of this system on a realistic and large dataset.
Address (down) Dublin, Ireland
Corporate Author Thesis
Publisher Springer Place of Publication Berlin Editor P. Clough; C. Foley; C. Gurrin; G.J.F. Jones; W. Kraaij; H. Lee; V. Murdoch
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN 978-3-642-20160-8 Medium
Area Expedition Conference ECIR
Notes DAG; RV;ADAS Approved no
Call Number Admin @ si @ RAK2011 Serial 1737
Permanent link to this record
 
 
Author Karel Paleček; David Geronimo; Frederic Lerasle
Title Pre-attention cues for person detection Type Conference Article
Year 2012 Publication Cognitive Behavioural Systems, COST 2102 International Training School Abbreviated Journal
Volume Issue Pages 225-235
Keywords
Abstract Current state-of-the-art person detectors have been proven reliable and achieve very good detection rates. However, the performance is often far from real time, which limits their use to low resolution images only. In this paper, we deal with candidate window generation problem for person detection, i.e. we want to reduce the computational complexity of a person detector by reducing the number of regions that has to be evaluated. We base our work on Alexe’s paper [1], which introduced several pre-attention cues for generic object detection. We evaluate these cues in the context of person detection and show that their performance degrades rapidly for scenes containing multiple objects of interest such as pictures from urban environment. We extend this set by new cues, which better suits our class-specific task. The cues are designed to be simple and efficient, so that they can be used in the pre-attention phase of a more complex sliding window based person detector.
Address (down) Dresden, Germany
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-34583-8 Medium
Area Expedition Conference COST-TS
Notes ADAS Approved no
Call Number Admin @ si @ PGL2012 Serial 2148
Permanent link to this record
 
 
Author Subhajit Maity; Sanket Biswas; Siladittya Manna; Ayan Banerjee; Josep Llados; Saumik Bhattacharya; Umapada Pal
Title SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation Type Conference Article
Year 2023 Publication 17th International Conference on Doccument Analysis and Recognition Abbreviated Journal
Volume 14187 Issue Pages 342–360
Keywords
Abstract Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visual feature extraction, etc. However, most of the existing works have ignored the crucial fact regarding the scarcity of labeled data. With growing internet connectivity to personal life, an enormous amount of documents had been available in the public domain and thus making data annotation a tedious task. We address this challenge using self-supervision and unlike, the few existing self-supervised document segmentation approaches which use text mining and textual labels, we use a complete vision-based approach in pre-training without any ground-truth label or its derivative. Instead, we generate pseudo-layouts from the document images to pre-train an image encoder to learn the document object representation and localization in a self-supervised framework before fine-tuning it with an object detection model. We show that our pipeline sets a new benchmark in this context and performs at par with the existing methods and the supervised counterparts, if not outperforms. The code is made publicly available at: this https URL
Address (down) Document Layout Analysis; Document
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 ICDAR
Notes DAG Approved no
Call Number Admin @ si @ MBM2023 Serial 3990
Permanent link to this record
 
 
Author Patricia Suarez; Dario Carpio; Angel Sappa; Henry Velesaca
Title Transformer based Image Dehazing Type Conference Article
Year 2022 Publication 16th IEEE International Conference on Signal Image Technology & Internet Based System Abbreviated Journal
Volume Issue Pages
Keywords atmospheric light; brightness component; computational cost; dehazing quality; haze-free image
Abstract This paper presents a novel approach to remove non homogeneous haze from real images. The proposed method consists mainly of image feature extraction, haze removal, and image reconstruction. To accomplish this challenging task, we propose an architecture based on transformers, which have been recently introduced and have shown great potential in different computer vision tasks. Our model is based on the SwinIR an image restoration architecture based on a transformer, but by modifying the deep feature extraction module, the depth level of the model, and by applying a combined loss function that improves styling and adapts the model for the non-homogeneous haze removal present in images. The obtained results prove to be superior to those obtained by state-of-the-art models.
Address (down) Dijon; France; October 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 SITIS
Notes MSIAU; no proj Approved no
Call Number Admin @ si @ SCS2022 Serial 3803
Permanent link to this record
 
 
Author Yi Xiao; Felipe Codevilla; Diego Porres; Antonio Lopez
Title Scaling Vision-Based End-to-End Autonomous Driving with Multi-View Attention Learning Type Conference Article
Year 2023 Publication International Conference on Intelligent Robots and Systems Abbreviated Journal
Volume Issue Pages
Keywords
Abstract On end-to-end driving, human driving demonstrations are used to train perception-based driving models by imitation learning. This process is supervised on vehicle signals (e.g., steering angle, acceleration) but does not require extra costly supervision (human labeling of sensor data). As a representative of such vision-based end-to-end driving models, CILRS is commonly used as a baseline to compare with new driving models. So far, some latest models achieve better performance than CILRS by using expensive sensor suites and/or by using large amounts of human-labeled data for training. Given the difference in performance, one may think that it is not worth pursuing vision-based pure end-to-end driving. However, we argue that this approach still has great value and potential considering cost and maintenance. In this paper, we present CIL++, which improves on CILRS by both processing higher-resolution images using a human-inspired HFOV as an inductive bias and incorporating a proper attention mechanism. CIL++ achieves competitive performance compared to models which are more costly to develop. We propose to replace CILRS with CIL++ as a strong vision-based pure end-to-end driving baseline supervised by only vehicle signals and trained by conditional imitation learning.
Address (down) Detroit; USA; October 2023
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 IROS
Notes ADAS Approved no
Call Number Admin @ si @ XCP2023 Serial 3930
Permanent link to this record
 
 
Author Fahad Shahbaz Khan; Muhammad Anwer Rao; Joost Van de Weijer; Michael Felsberg; J.Laaksonen
Title Deep semantic pyramids for human attributes and action recognition Type Conference Article
Year 2015 Publication Image Analysis, Proceedings of 19th Scandinavian Conference , SCIA 2015 Abbreviated Journal
Volume 9127 Issue Pages 341-353
Keywords Action recognition; Human attributes; Semantic pyramids
Abstract Describing persons and their actions is a challenging problem due to variations in pose, scale and viewpoint in real-world images. Recently, semantic pyramids approach [1] for pose normalization has shown to provide excellent results for gender and action recognition. The performance of semantic pyramids approach relies on robust image description and is therefore limited due to the use of shallow local features. In the context of object recognition [2] and object detection [3], convolutional neural networks (CNNs) or deep features have shown to improve the performance over the conventional shallow features.
We propose deep semantic pyramids for human attributes and action recognition. The method works by constructing spatial pyramids based on CNNs of different part locations. These pyramids are then combined to obtain a single semantic representation. We validate our approach on the Berkeley and 27 Human Attributes datasets for attributes classification. For action recognition, we perform experiments on two challenging datasets: Willow and PASCAL VOC 2010. The proposed deep semantic pyramids provide a significant gain of 17.2%, 13.9%, 24.3% and 22.6% compared to the standard shallow semantic pyramids on Berkeley, 27 Human Attributes, Willow and PASCAL VOC 2010 datasets respectively. Our results also show that deep semantic pyramids outperform conventional CNNs based on the full bounding box of the person. Finally, we compare our approach with state-of-the-art methods and show a gain in performance compared to best methods in literature.
Address (down) Denmark; Copenhagen; June 2015
Corporate Author Thesis
Publisher Springer International Publishing Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-319-19664-0 Medium
Area Expedition Conference SCIA
Notes LAMP; 600.068; 600.079;ADAS Approved no
Call Number Admin @ si @ KRW2015b Serial 2672
Permanent link to this record
 
 
Author Antonio Esteban Lansaque; Carles Sanchez; Agnes Borras; Marta Diez-Ferrer; Antoni Rosell; Debora Gil
Title Stable Airway Center Tracking for Bronchoscopic Navigation Type Conference Article
Year 2016 Publication 28th Conference of the international Society for Medical Innovation and Technology Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Bronchoscopists use X‐ray fluoroscopy to guide bronchoscopes to the lesion to be biopsied without any kind of incisions. Reducing exposure to X‐ray is important for both patients and doctors but alternatives like electromagnetic navigation require specific equipment and increase the cost of the clinical procedure. We propose a guiding system based on the extraction of airway centers from intra‐operative videos. Such anatomical landmarks could be
matched to the airway centerline extracted from a pre‐planned CT to indicate the best path to the lesion. We present an extraction of lumen centers
from intra‐operative videos based on tracking of maximal stable regions of energy maps.
Address (down) Delft; Rotterdam; Leiden; The Netherlands; October 2016
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 SMIT
Notes IAM; Approved no
Call Number Admin @ si @ LSB2016a Serial 2856
Permanent link to this record
 
 
Author Daniel Ponsa; Antonio Lopez
Title Cascade of Classifiers for Vehicle Detection Type Conference Article
Year 2007 Publication Advanced Concepts for Intelligent Vision Systems, LNCS 4678, volume 1, pp. 980–989 Abbreviated Journal
Volume Issue Pages
Keywords vehicle detection
Abstract
Address (down) Delft (Netherlands)
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 ADAS Approved no
Call Number ADAS @ adas @ PoL2007c Serial 935
Permanent link to this record
 
 
Author Akshita Gupta; Sanath Narayan; Salman Khan; Fahad Shahbaz Khan; Ling Shao; Joost Van de Weijer
Title Generative Multi-Label Zero-Shot Learning Type Journal Article
Year 2023 Publication IEEE Transactions on Pattern Analysis and Machine Intelligence Abbreviated Journal TPAMI
Volume 45 Issue 12 Pages 14611-14624
Keywords Generalized zero-shot learning; Multi-label classification; Zero-shot object detection; Feature synthesis
Abstract Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label generative adversarial network (GAN) based approaches learn to directly synthesize the class-specific visual features from the corresponding class attribute embeddings. However, synthesizing multi-label features from GANs is still unexplored in the context of zero-shot setting. When multiple objects occur jointly in a single image, a critical question is how to effectively fuse multi-class information. In this work, we introduce different fusion approaches at the attribute-level, feature-level and cross-level (across attribute and feature-levels) for synthesizing multi-label features from their corresponding multi-label class embeddings. To the best of our knowledge, our work is the first to tackle the problem of multi-label feature synthesis in the (generalized) zero-shot setting. Our cross-level fusion-based generative approach outperforms the state-of-the-art on three zero-shot benchmarks: NUS-WIDE, Open Images and MS COCO. Furthermore, we show the generalization capabilities of our fusion approach in the zero-shot detection task on MS COCO, achieving favorable performance against existing methods.
Address (down) December 2023
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes LAMP; PID2021-128178OB-I00 Approved no
Call Number Admin @ si @ Serial 3853
Permanent link to this record
 
 
Author Iban Berganzo-Besga; Hector A. Orengo; Felipe Lumbreras; Paloma Aliende; Monica N. Ramsey
Title Automated detection and classification of multi-cell Phytoliths using Deep Learning-Based Algorithms Type Journal Article
Year 2022 Publication Journal of Archaeological Science Abbreviated Journal JArchSci
Volume 148 Issue Pages 105654
Keywords
Abstract This paper presents an algorithm for automated detection and classification of multi-cell phytoliths, one of the major components of many archaeological and paleoenvironmental deposits. This identification, based on phytolith wave pattern, is made using a pretrained VGG19 deep learning model. This approach has been tested in three key phytolith genera for the study of agricultural origins in Near East archaeology: Avena, Hordeum and Triticum. Also, this classification has been validated at species-level using Triticum boeoticum and dicoccoides images. Due to the diversity of microscopes, cameras and chemical treatments that can influence images of phytolith slides, three types of data augmentation techniques have been implemented: rotation of the images at 45-degree angles, random colour and brightness jittering, and random blur/sharpen. The implemented workflow has resulted in an overall accuracy of 93.68% for phytolith genera, improving previous attempts. The algorithm has also demonstrated its potential to automatize the classification of phytoliths species with an overall accuracy of 100%. The open code and platforms employed to develop the algorithm assure the method's accessibility, reproducibility and reusability.
Address (down) December 2022
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes MSIAU; MACO; 600.167 Approved no
Call Number Admin @ si @ BOL2022 Serial 3753
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 (down) 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 (down) 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 Xialei Liu
Title Visual recognition in the wild: learning from rankings in small domains and continual learning in new domains Type Book Whole
Year 2019 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 application, such as image classification, detection and segmentation. In this thesis we address two limitations of CNNs. Training deep CNNs requires huge amounts of labeled data, which is expensive and labor intensive to collect. Another limitation is that training CNNs in a continual learning setting is still an open research question. Catastrophic forgetting is very likely when adapting trained models to new environments or new tasks. Therefore, in this thesis, we aim to improve CNNs for applications with limited data and to adapt CNNs continually to new tasks.
Self-supervised learning leverages unlabelled data by introducing an auxiliary task for which data is abundantly available. In the first part of the thesis, we show how rankings can be used as a proxy self-supervised task for regression problems. Then we propose an efficient backpropagation technique for Siamese networks which prevents the redundant computation introduced by the multi-branch network architecture. In addition, we show that measuring network uncertainty on the self-supervised proxy task is a good measure of informativeness of unlabeled data. This can be used to drive an algorithm for active learning. We then apply our framework on two regression problems: Image Quality Assessment (IQA) and Crowd Counting. For both, we show how to automatically generate ranked image sets from unlabeled data. Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results. We further show that active learning using rankings can reduce labeling effort by up to 50\% for both IQA and crowd counting.
In the second part of the thesis, we propose two approaches to avoiding catastrophic forgetting in sequential task learning scenarios. The first approach is derived from Elastic Weight Consolidation, which uses a diagonal Fisher Information Matrix (FIM) to measure the importance of the parameters of the network. However the diagonal assumption is unrealistic. Therefore, we approximately diagonalize the FIM using a set of factorized rotation parameters. This leads to significantly better performance on continual learning of sequential tasks. For the second approach, we show that forgetting manifests differently at different layers in the network and propose a hybrid approach where distillation is used in the feature extractor and replay in the classifier via feature generation. Our method addresses the limitations of generative image replay and probability distillation (i.e. learning without forgetting) and can naturally aggregate new tasks in a single, well-calibrated classifier. Experiments confirm that our proposed approach outperforms the baselines and some start-of-the-art methods.
Address (down) December 2019
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 978-84-121011-4-0 Medium
Area Expedition Conference
Notes LAMP; 600.120 Approved no
Call Number Admin @ si @ Liu2019 Serial 3396
Permanent link to this record
 
 
Author Arnau Baro; Pau Riba; Alicia Fornes
Title Musigraph: Optical Music Recognition Through Object Detection and Graph Neural Network Type Conference Article
Year 2022 Publication Frontiers in Handwriting Recognition. International Conference on Frontiers in Handwriting Recognition (ICFHR2022) Abbreviated Journal
Volume 13639 Issue Pages 171-184
Keywords Object detection; Optical music recognition; Graph neural network
Abstract During the last decades, the performance of optical music recognition has been increasingly improving. However, and despite the 2-dimensional nature of music notation (e.g. notes have rhythm and pitch), most works treat musical scores as a sequence of symbols in one dimension, which make their recognition still a challenge. Thus, in this work we explore the use of graph neural networks for musical score recognition. First, because graphs are suited for n-dimensional representations, and second, because the combination of graphs with deep learning has shown a great performance in similar applications. Our methodology consists of: First, we will detect each isolated/atomic symbols (those that can not be decomposed in more graphical primitives) and the primitives that form a musical symbol. Then, we will build the graph taking as root node the notehead and as leaves those primitives or symbols that modify the note’s rhythm (stem, beam, flag) or pitch (flat, sharp, natural). Finally, the graph is translated into a human-readable character sequence for a final transcription and evaluation. Our method has been tested on more than five thousand measures, showing promising results.
Address (down) December 04 – 07, 2022; Hyderabad, India
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ICFHR
Notes DAG; 600.162; 600.140; 602.230 Approved no
Call Number Admin @ si @ BRF2022b Serial 3740
Permanent link to this record