Home [91–100] << 101 102 103 104 105 106 107 108 109 110 >> [111–120]
List View
 | 
Citations
 | 
Details
   web
Records
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 (up) 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 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 Ruben Tito; Dimosthenis Karatzas; Ernest Valveny
Title Document Collection Visual Question Answering Type Conference Article
Year 2021 Publication 16th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume 12822 Issue Pages 778-792
Keywords Document collection; Visual Question Answering
Abstract (up) Current tasks and methods in Document Understanding aims to process documents as single elements. However, documents are usually organized in collections (historical records, purchase invoices), that provide context useful for their interpretation. To address this problem, we introduce Document Collection Visual Question Answering (DocCVQA) a new dataset and related task, where questions are posed over a whole collection of document images and the goal is not only to provide the answer to the given question, but also to retrieve the set of documents that contain the information needed to infer the answer. Along with the dataset we propose a new evaluation metric and baselines which provide further insights to the new dataset and task.
Address
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 ICDAR
Notes DAG; 600.121 Approved no
Call Number Admin @ si @ TKV2021 Serial 3622
Permanent link to this record
 
 
Author Ali Furkan Biten; R. Tito; Andres Mafla; Lluis Gomez; Marçal Rusiñol; C.V. Jawahar; Ernest Valveny; Dimosthenis Karatzas
Title Scene Text Visual Question Answering Type Conference Article
Year 2019 Publication 18th IEEE International Conference on Computer Vision Abbreviated Journal
Volume Issue Pages 4291-4301
Keywords
Abstract (up) Current visual question answering datasets do not consider the rich semantic information conveyed by text within an image. In this work, we present a new dataset, ST-VQA, that aims to highlight the importance of exploiting highlevel semantic information present in images as textual cues in the Visual Question Answering process. We use this dataset to define a series of tasks of increasing difficulty for which reading the scene text in the context provided by the visual information is necessary to reason and generate an appropriate answer. We propose a new evaluation metric for these tasks to account both for reasoning errors as well as shortcomings of the text recognition module. In addition we put forward a series of baseline methods, which provide further insight to the newly released dataset, and set the scene for further research.
Address Seul; Corea; October 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 ICCV
Notes DAG; 600.129; 600.135; 601.338; 600.121 Approved no
Call Number Admin @ si @ BTM2019b Serial 3285
Permanent link to this record
 
 
Author Josep Llados;Horst Bunke; Enric Marti
Title Using Cyclic String Matching to Find Rotational and Reflectional Symmetries in Shapes Type Conference Article
Year 1997 Publication Intelligent Robots: Sensing, Modeling and Planning Abbreviated Journal
Volume Issue Pages 164-179
Keywords
Abstract (up) Dagstuhl Workshop
Address
Corporate Author Thesis
Publisher World Scientific Press Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 9810231857 Medium
Area Expedition Conference
Notes DAG;IAM; Approved no
Call Number IAM @ iam @ LBM1997b Serial 1563
Permanent link to this record
 
 
Author Fei Yang; Yaxing Wang; Luis Herranz; Yongmei Cheng; Mikhail Mozerov
Title A Novel Framework for Image-to-image Translation and Image Compression Type Journal Article
Year 2022 Publication Neurocomputing Abbreviated Journal NEUCOM
Volume 508 Issue Pages 58-70
Keywords
Abstract (up) Data-driven paradigms using machine learning are becoming ubiquitous in image processing and communications. In particular, image-to-image (I2I) translation is a generic and widely used approach to image processing problems, such as image synthesis, style transfer, and image restoration. At the same time, neural image compression has emerged as a data-driven alternative to traditional coding approaches in visual communications. In this paper, we study the combination of these two paradigms into a joint I2I compression and translation framework, focusing on multi-domain image synthesis. We first propose distributed I2I translation by integrating quantization and entropy coding into an I2I translation framework (i.e. I2Icodec). In practice, the image compression functionality (i.e. autoencoding) is also desirable, requiring to deploy alongside I2Icodec a regular image codec. Thus, we further propose a unified framework that allows both translation and autoencoding capabilities in a single codec. Adaptive residual blocks conditioned on the translation/compression mode provide flexible adaptation to the desired functionality. The experiments show promising results in both I2I translation and image compression using a single model.
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 LAMP Approved no
Call Number Admin @ si @ YWH2022 Serial 3679
Permanent link to this record
 
 
Author Adria Molina; Lluis Gomez; Oriol Ramos Terrades; Josep Llados
Title A Generic Image Retrieval Method for Date Estimation of Historical Document Collections Type Conference Article
Year 2022 Publication Document Analysis Systems.15th IAPR International Workshop, (DAS2022) Abbreviated Journal
Volume 13237 Issue Pages 583–597
Keywords Date estimation; Document retrieval; Image retrieval; Ranking loss; Smooth-nDCG
Abstract (up) Date estimation of historical document images is a challenging problem, with several contributions in the literature that lack of the ability to generalize from one dataset to others. This paper presents a robust date estimation system based in a retrieval approach that generalizes well in front of heterogeneous collections. We use a ranking loss function named smooth-nDCG to train a Convolutional Neural Network that learns an ordination of documents for each problem. One of the main usages of the presented approach is as a tool for historical contextual retrieval. It means that scholars could perform comparative analysis of historical images from big datasets in terms of the period where they were produced. We provide experimental evaluation on different types of documents from real datasets of manuscript and newspaper images.
Address La Rochelle, France; May 22–25, 2022
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference DAS
Notes DAG; 600.140; 600.121 Approved no
Call Number Admin @ si @ MGR2022 Serial 3694
Permanent link to this record
 
 
Author Sergio Escalera; Marti Soler; Stephane Ayache; Umut Guçlu; Jun Wan; Meysam Madadi; Xavier Baro; Hugo Jair Escalante; Isabelle Guyon
Title ChaLearn Looking at People: Inpainting and Denoising Challenges Type Book Chapter
Year 2019 Publication The Springer Series on Challenges in Machine Learning Abbreviated Journal
Volume Issue Pages 23-44
Keywords
Abstract (up) Dealing with incomplete information is a well studied problem in the context of machine learning and computational intelligence. However, in the context of computer vision, the problem has only been studied in specific scenarios (e.g., certain types of occlusions in specific types of images), although it is common to have incomplete information in visual data. This chapter describes the design of an academic competition focusing on inpainting of images and video sequences that was part of the competition program of WCCI2018 and had a satellite event collocated with ECCV2018. The ChaLearn Looking at People Inpainting Challenge aimed at advancing the state of the art on visual inpainting by promoting the development of methods for recovering missing and occluded information from images and video. Three tracks were proposed in which visual inpainting might be helpful but still challenging: human body pose estimation, text overlays removal and fingerprint denoising. This chapter describes the design of the challenge, which includes the release of three novel datasets, and the description of evaluation metrics, baselines and evaluation protocol. The results of the challenge are analyzed and discussed in detail and conclusions derived from this event are outlined.
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 HuPBA; no proj Approved no
Call Number Admin @ si @ ESA2019 Serial 3327
Permanent link to this record
 
 
Author Ferran Poveda; Debora Gil ;Albert Andaluz ;Enric Marti
Title Multiscale Tractography for Representing Heart Muscular Architecture Type Conference Article
Year 2011 Publication In MICCAI 2011 Workshop on Computational Diffusion MRI Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Deep understanding of myocardial structure of the heart would unravel crucial knowledge for clinical and medical procedures. Although the muscular architecture of the heart has been debated by countless researchers, the controversy is still alive. Diffusion Tensor MRI, DT-MRI, is a unique imaging technique for computational validation of the muscular structure of the heart. By the complex arrangement of myocites, existing techniques can not provide comprehensive descriptions of the global muscular architecture. In this paper we introduce a multiresolution reconstruction technique based on DT-MRI streamlining for simplified global myocardial model generation. Our reconstructions can restore the most complex myocardial structures and indicate a global helical organization
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language English Summary Language english Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference CDRMI
Notes IAM Approved no
Call Number IAM @ iam @ PGA2011 Serial 1681
Permanent link to this record
 
 
Author Swathikiran Sudhakaran; Sergio Escalera; Oswald Lanz
Title Gate-Shift Networks for Video Action Recognition Type Conference Article
Year 2020 Publication 33rd IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Deep 3D CNNs for video action recognition are designed to learn powerful representations in the joint spatio-temporal feature space. In practice however, because of the large number of parameters and computations involved, they may under-perform in the lack of sufficiently large datasets for training them at scale. In this paper we introduce spatial gating in spatial-temporal decomposition of 3D kernels. We implement this concept with Gate-Shift Module (GSM). GSM is lightweight and turns a 2D-CNN into a highly efficient spatio-temporal feature extractor. With GSM plugged in, a 2D-CNN learns to adaptively route features through time and combine them, at almost no additional parameters and computational overhead. We perform an extensive evaluation of the proposed module to study its effectiveness in video action recognition, achieving state-of-the-art results on Something Something-V1 and Diving48 datasets, and obtaining competitive results on EPIC-Kitchens with far less model complexity.
Address Virtual CVPR
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 CVPR
Notes HuPBA; no proj Approved no
Call Number Admin @ si @ SEL2020 Serial 3438
Permanent link to this record
 
 
Author Hassan Ahmed Sial; S. Sancho; Ramon Baldrich; Robert Benavente; Maria Vanrell
Title Color-based data augmentation for Reflectance Estimation Type Conference Article
Year 2018 Publication 26th Color Imaging Conference Abbreviated Journal
Volume Issue Pages 284-289
Keywords
Abstract (up) Deep convolutional architectures have shown to be successful frameworks to solve generic computer vision problems. The estimation of intrinsic reflectance from single image is not a solved problem yet. Encoder-Decoder architectures are a perfect approach for pixel-wise reflectance estimation, although it usually suffers from the lack of large datasets. Lack of data can be partially solved with data augmentation, however usual techniques focus on geometric changes which does not help for reflectance estimation. In this paper we propose a color-based data augmentation technique that extends the training data by increasing the variability of chromaticity. Rotation on the red-green blue-yellow plane of an opponent space enable to increase the training set in a coherent and sound way that improves network generalization capability for reflectance estimation. We perform some experiments on the Sintel dataset showing that our color-based augmentation increase performance and overcomes one of the state-of-the-art methods.
Address Vancouver; November 2018
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 CIC
Notes CIC Approved no
Call Number Admin @ si @ SSB2018a Serial 3129
Permanent link to this record
 
 
Author Xinhang Song; Shuqiang Jiang; Luis Herranz; Chengpeng Chen
Title Learning Effective RGB-D Representations for Scene Recognition Type Journal Article
Year 2019 Publication IEEE Transactions on Image Processing Abbreviated Journal TIP
Volume 28 Issue 2 Pages 980-993
Keywords
Abstract (up) Deep convolutional networks can achieve impressive results on RGB scene recognition thanks to large data sets such as places. In contrast, RGB-D scene recognition is still underdeveloped in comparison, due to two limitations of RGB-D data we address in this paper. The first limitation is the lack of depth data for training deep learning models. Rather than fine tuning or transferring RGB-specific features, we address this limitation by proposing an architecture and a two-step training approach that directly learns effective depth-specific features using weak supervision via patches. The resulting RGB-D model also benefits from more complementary multimodal features. Another limitation is the short range of depth sensors (typically 0.5 m to 5.5 m), resulting in depth images not capturing distant objects in the scenes that RGB images can. We show that this limitation can be addressed by using RGB-D videos, where more comprehensive depth information is accumulated as the camera travels across the scenes. Focusing on this scenario, we introduce the ISIA RGB-D video data set to evaluate RGB-D scene recognition with videos. Our video recognition architecture combines convolutional and recurrent neural networks that are trained in three steps with increasingly complex data to learn effective features (i.e., patches, frames, and sequences). Our approach obtains the state-of-the-art performances on RGB-D image (NYUD2 and SUN RGB-D) and video (ISIA RGB-D) scene recognition.
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 LAMP; 600.141; 600.120 Approved no
Call Number Admin @ si @ SJH2019 Serial 3247
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 (up) 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 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 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 (up) 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 Cesar de Souza; Adrien Gaidon; Yohann Cabon; Antonio Lopez
Title Procedural Generation of Videos to Train Deep Action Recognition Networks Type Conference Article
Year 2017 Publication 30th IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal
Volume Issue Pages 2594-2604
Keywords
Abstract (up) Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for ”Procedural Human Action Videos”. It contains a total of 39, 982 videos, with more than 1, 000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We introduce a deep multi-task representation learning architecture to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF101 and HMDB51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, significantly
outperforming fine-tuning state-of-the-art unsupervised generative models of videos.
Address Honolulu; Hawaii; July 2017
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 CVPR
Notes ADAS; 600.076; 600.085; 600.118 Approved no
Call Number Admin @ si @ SGC2017 Serial 3051
Permanent link to this record
 
 
Author Kai Wang
Title Continual learning for hierarchical classification, few-shot recognition, and multi-modal learning Type Book Whole
Year 2022 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Deep learning has drastically changed computer vision in the past decades and achieved great success in many applications, such as image classification, retrieval, detection, and segmentation thanks to the emergence of neural networks. Typically, for most applications, these networks are presented with examples from all tasks they are expected to perform. However, for many applications, this is not a realistic
scenario, and an algorithm is required to learn tasks sequentially. Continual learning proposes theory and methods for this scenario.
The main challenge for continual learning systems is called catastrophic forgetting and refers to a significant drop in performance on previous tasks. To tackle this problem, three main branches of methods have been explored to alleviate the forgetting in continual learning. They are regularization-based methods, rehearsalbased methods, and parameter isolation-based methods. However, most of them are focused on image classification tasks. Continual learning of many computer vision fields has still not been well-explored. Thus, in this thesis, we extend the continual learning knowledge to meta learning, we propose a method for the incremental learning of hierarchical relations for image classification, we explore image recognition in online continual learning, and study continual learning for cross-modal learning.
In this thesis, we explore the usage of image rehearsal when addressing the incremental meta learning problem. Observing that existingmethods fail to improve performance with saved exemplars, we propose to mix exemplars with current task data and episode-level distillation to overcome forgetting in incremental meta learning. Next, we study a more realistic image classification scenario where each class has multiple granularity levels. Only one label is present at any time, which requires the model to infer if the provided label has a hierarchical relation with any already known label. In experiments, we show that the estimated hierarchy information can be beneficial in both the training and inference stage.
For the online continual learning setting, we investigate the usage of intermediate feature replay. In this case, the training samples are only observed by the model only one time. Here we fix thememory buffer for feature replay and compare the effectiveness of saving features from different layers. Finally, we investigate multi-modal continual learning, where an image encoder is cooperating with a semantic branch. We consider the continual learning of both zero-shot learning and cross-modal retrieval problems.
Address July, 2022
Corporate Author Thesis Ph.D. thesis
Publisher Place of Publication Editor Luis Herranz;Joost Van de Weijer
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-124793-2-4 Medium
Area Expedition Conference
Notes LAMP Approved no
Call Number Admin @ si @ Wan2022 Serial 3714
Permanent link to this record