| Home | [71–80] << 81 82 83 84 85 86 87 88 89 90 >> [91–100] |
|
| Records | |||||
|---|---|---|---|---|---|
| Author | Lichao Zhang | ||||
| Title | Towards end-to-end Networks for Visual Tracking in RGB and TIR Videos | Type | Book Whole | ||
| Year | 2019 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
| Volume | Issue | Pages  |
|||
| Keywords | |||||
| Abstract | In the current work, we identify several problems of current tracking systems. The lack of large-scale labeled datasets hampers the usage of deep learning, especially end-to-end training, for tracking in TIR images. Therefore, many methods for tracking on TIR data are still based on hand-crafted features. This situation also happens in multi-modal tracking, e.g. RGB-T tracking. Another reason, which hampers the development of RGB-T tracking, is that there exists little research on the fusion mechanisms for combining information from RGB and TIR modalities. One of the crucial components of most trackers is the update module. For the currently existing end-to-end tracking architecture, e.g, Siamese trackers, the online model update is still not taken into consideration at the training stage. They use no-update or a linear update strategy during the inference stage. While such a hand-crafted approach to updating has led to improved results, its simplicity limits the potential gain likely to be obtained by learning to update.
To address the data-scarcity for TIR and RGB-T tracking, we use image-to-image translation to generate a large-scale synthetic TIR dataset. This dataset allows us to perform end-to-end training for TIR tracking. Furthermore, we investigate several fusion mechanisms for RGB-T tracking. The multi-modal trackers are also trained in an end-to-end manner on the synthetic data. To improve the standard online update, we pose the updating step as an optimization problem which can be solved by training a neural network. Our approach thereby reduces the hand-crafted components in the tracking pipeline and sets a further step in the direction of a complete end-to-end trained tracking network which also considers updating during optimization. |
||||
| Address | November 2019 | ||||
| Corporate Author | Thesis | Ph.D. thesis | |||
| Publisher | Ediciones Graficas Rey | Place of Publication | Editor | Joost Van de Weijer;Abel Gonzalez;Fahad Shahbaz Khan | |
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 978-84-1210011-1-9 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | LAMP; 600.141; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ Zha2019 | Serial | 3393 | ||
| Permanent link to this record | |||||
| Author | Lu Yu | ||||
| Title | Semantic Representation: From Color to Deep Embeddings | Type | Book Whole | ||
| Year | 2019 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | One of the fundamental problems of computer vision is to represent images with compact semantically relevant embeddings. These embeddings could then be used in a wide variety of applications, such as image retrieval, object detection, and video search. The main objective of this thesis is to study image embeddings from two aspects: color embeddings and deep embeddings.
In the first part of the thesis we start from hand-crafted color embeddings. We propose a method to order the additional color names according to their complementary nature with the basic eleven color names. This allows us to compute color name representations with high discriminative power of arbitrary length. Psychophysical experiments confirm that our proposed method outperforms baseline approaches. Secondly, we learn deep color embeddings from weakly labeled data by adding an attention strategy. The attention branch is able to correctly identify the relevant regions for each class. The advantage of our approach is that it can learn color names for specific domains for which no pixel-wise labels exists. In the second part of the thesis, we focus on deep embeddings. Firstly, we address the problem of compressing large embedding networks into small networks, while maintaining similar performance. We propose to distillate the metrics from a teacher network to a student network. Two new losses are introduced to model the communication of a deep teacher network to a small student network: one based on an absolute teacher, where the student aims to produce the same embeddings as the teacher, and one based on a relative teacher, where the distances between pairs of data points is communicated from the teacher to the student. In addition, various aspects of distillation have been investigated for embeddings, including hint and attention layers, semi-supervised learning and cross quality distillation. Finally, another aspect of deep metric learning, namely lifelong learning, is studied. We observed some drift occurs during training of new tasks for metric learning. A method to estimate the semantic drift based on the drift which is experienced by data of the current task during its training is introduced. Having this estimation, previous tasks can be compensated for this drift, thereby improving their performance. Furthermore, we show that embedding networks suffer significantly less from catastrophic forgetting compared to classification networks when learning new tasks. |
||||
| Address | November 2019 | ||||
| Corporate Author | Thesis | Ph.D. thesis | |||
| Publisher | Ediciones Graficas Rey | Place of Publication | Editor | Joost Van de Weijer;Yongmei Cheng | |
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 978-84-121011-3-3 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | LAMP; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ Yu2019 | Serial | 3394 | ||
| Permanent link to this record | |||||
| Author | Albert Berenguel | ||||
| Title | Analysis of background textures in banknotes and identity documents for counterfeit detection | Type | Book Whole | ||
| Year | 2019 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | Counterfeiting and piracy are a form of theft that has been steadily growing in recent years. A counterfeit is an unauthorized reproduction of an authentic/genuine object. Banknotes and identity documents are two common objects of counterfeiting. The former is used by organized criminal groups to finance a variety of illegal activities or even to destabilize entire countries due the inflation effect. Generally, in order to run their illicit businesses, counterfeiters establish companies and bank accounts using fraudulent identity documents. The illegal activities generated by counterfeit banknotes and identity documents has a damaging effect on business, the economy and the general population. To fight against counterfeiters, governments and authorities around the globe cooperate and develop security features to protect their security documents. Many of the security features in identity documents can also be found in banknotes. In this dissertation we focus our efforts in detecting the counterfeit banknotes and identity documents by analyzing the security features at the background printing. Background areas on secure documents contain fine-line patterns and designs that are difficult to reproduce without the manufacturers cutting-edge printing equipment. Our objective is to find the loose of resolution between the genuine security document and the printed counterfeit version with a publicly available commercial printer. We first present the most complete survey to date in identity and banknote security features. The compared algorithms and systems are based on computer vision and machine learning. Then we advance to present the banknote and identity counterfeit dataset we have built and use along all this thesis. Afterwards, we evaluate and adapt algorithms in the literature for the security background texture analysis. We study this problem from the point of view of robustness, computational efficiency and applicability into a real and non-controlled industrial scenario, proposing key insights to use these algorithms. Next, within the industrial environment of this thesis, we build a complete service oriented architecture to detect counterfeit documents. The mobile application and the server framework intends to be used even by non-expert document examiners to spot counterfeits. Later, we re-frame the problem of background texture counterfeit detection as a full-reference game of spotting the differences, by alternating glimpses between a counterfeit and a genuine background using recurrent neural networks. Finally, we deal with the lack of counterfeit samples, studying different approaches based on anomaly detection. | ||||
| Address | November 2019 | ||||
| Corporate Author | Thesis | Ph.D. thesis | |||
| Publisher | Ediciones Graficas Rey | Place of Publication | Editor | Oriol Ramos Terrades;Josep Llados | |
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 978-84-121011-2-6 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | DAG; 600.140; 600.121 | Approved | no | ||
| Call Number | Admin @ si @ Ber2019 | Serial | 3395 | ||
| 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 | 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 | Yaxing Wang | ||||
| Title | Transferring and Learning Representations for Image Generation and Translation | Type | Book Whole | ||
| Year | 2020 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | Image generation is arguably one of the most attractive, compelling, and challenging tasks in computer vision. Among the methods which perform image generation, generative adversarial networks (GANs) play a key role. The most common image generation models based on GANs can be divided into two main approaches. The first one, called simply image generation takes random noise as an input and synthesizes an image which follows the same distribution as the images in the training set. The second class, which is called image-to-image translation, aims to map an image from a source domain to one that is indistinguishable from those in the target domain. Image-to-image translation methods can further be divided into paired and unpaired image-to-image translation based on whether they require paired data or not. In this thesis, we aim to address some challenges of both image generation and image-to-image generation.GANs highly rely upon having access to vast quantities of data, and fail to generate realistic images from random noise when applied to domains with few images. To address this problem, we aim to transfer knowledge from a model trained on a large dataset (source domain) to the one learned on limited data (target domain). We find that both GANs andconditional GANs can benefit from models trained on large datasets. Our experiments show that transferring the discriminator is more important than the generator. Using both the generator and discriminator results in the best performance. We found, however, that this method suffers from overfitting, since we update all parameters to adapt to the target data. We propose a novel architecture, which is tailored to address knowledge transfer to very small target domains. Our approach effectively exploreswhich part of the latent space is more related to the target domain. Additionally, the proposed method is able to transfer knowledge from multiple pretrained GANs. Although image-to-image translation has achieved outstanding performance, it still facesseveral problems. First, for translation between complex domains (such as translations between different modalities) image-to-image translation methods require paired data. We show that when only some of the pairwise translations have been seen (i.e. during training), we can infer the remaining unseen translations (where training pairs are not available). We propose a new approach where we align multiple encoders and decoders in such a way that the desired translation can be obtained by simply cascadingthe source encoder and the target decoder, even when they have not interacted during the training stage (i.e. unseen). Second, we address the issue of bias in image-to-image translation. Biased datasets unavoidably contain undesired changes, which are dueto the fact that the target dataset has a particular underlying visual distribution. We use carefully designed semantic constraints to reduce the effects of the bias. The semantic constraint aims to enforce the preservation of desired image properties. Finally, current approaches fail to generate diverse outputs or perform scalable image transfer in a single model. To alleviate this problem, we propose a scalable and diverse image-to-image translation. We employ random noise to control the diversity. The scalabitlity is determined by conditioning the domain label.computer vision, deep learning, imitation learning, adversarial generative networks, image generation, image-to-image translation. | ||||
| Address | January 2020 | ||||
| Corporate Author | Thesis | Ph.D. thesis | |||
| Publisher | Ediciones Graficas Rey | Place of Publication | Editor | Joost Van de Weijer;Abel Gonzalez;Luis Herranz | |
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 978-84-121011-5-7 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | LAMP; 600.141; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ Wan2020 | Serial | 3397 | ||
| Permanent link to this record | |||||
| Author | Sergio Escalera; Stephane Ayache; Jun Wan; Meysam Madadi; Umut Guçlu; Xavier Baro | ||||
| Title | Inpainting and Denoising Challenges | Type | Book Whole | ||
| Year | 2019 | Publication | The Springer Series on Challenges in Machine Learning | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | The problem of dealing with missing or incomplete data in machine learning and computer vision arises in many applications. Recent strategies make use of generative models to impute missing or corrupted data. Advances in computer vision using deep generative models have found applications in image/video processing, such as denoising, restoration, super-resolution, or inpainting.
Inpainting and Denoising Challenges comprises recent efforts dealing with image and video inpainting tasks. This includes winning solutions to the ChaLearn Looking at People inpainting and denoising challenges: human pose recovery, video de-captioning and fingerprint restoration. This volume starts with a wide review on image denoising, retracing and comparing various methods from the pioneer signal processing methods, to machine learning approaches with sparse and low-rank models, and recent deep learning architectures with autoencoders and variants. The following chapters present results from the Challenge, including three competition tasks at WCCI and ECML 2018. The top best approaches submitted by participants are described, showing interesting contributions and innovating methods. The last two chapters propose novel contributions and highlight new applications that benefit from image/video inpainting. |
||||
| 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 menciona | Approved | no | ||
| Call Number | Admin @ si @ EAW2019 | Serial | 3398 | ||
| Permanent link to this record | |||||
| Author | Hugo Jair Escalante; Sergio Escalera; Isabelle Guyon; Xavier Baro; Yagmur Gucluturk; Umut Guçlu; Marcel van Gerven | ||||
| Title | Explainable and Interpretable Models in Computer Vision and Machine Learning | Type | Book Whole | ||
| Year | 2018 | Publication | The Springer Series on Challenges in Machine Learning | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | This book compiles leading research on the development of explainable and interpretable machine learning methods in the context of computer vision and machine learning.
Research progress in computer vision and pattern recognition has led to a variety of modeling techniques with almost human-like performance. Although these models have obtained astounding results, they are limited in their explainability and interpretability: what is the rationale behind the decision made? what in the model structure explains its functioning? Hence, while good performance is a critical required characteristic for learning machines, explainability and interpretability capabilities are needed to take learning machines to the next step to include them in decision support systems involving human supervision. This book, written by leading international researchers, addresses key topics of explainability and interpretability, including the following: ·Evaluation and Generalization in Interpretable Machine Learning ·Explanation Methods in Deep Learning ·Learning Functional Causal Models with Generative Neural Networks ·Learning Interpreatable Rules for Multi-Label Classification ·Structuring Neural Networks for More Explainable Predictions ·Generating Post Hoc Rationales of Deep Visual Classification Decisions ·Ensembling Visual Explanations ·Explainable Deep Driving by Visualizing Causal Attention ·Interdisciplinary Perspective on Algorithmic Job Candidate Search ·Multimodal Personality Trait Analysis for Explainable Modeling of Job Interview Decisions ·Inherent Explainability Pattern Theory-based Video Event Interpretations |
||||
| 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 menciona | Approved | no | ||
| Call Number | Admin @ si @ EEG2018 | Serial | 3399 | ||
| Permanent link to this record | |||||
| Author | Sangeeth Reddy; Minesh Mathew; Lluis Gomez; Marçal Rusiñol; Dimosthenis Karatzas; C.V. Jawahar | ||||
| Title | RoadText-1K: Text Detection and Recognition Dataset for Driving Videos | Type | Conference Article | ||
| Year | 2020 | Publication | IEEE International Conference on Robotics and Automation | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | Perceiving text is crucial to understand semantics of outdoor scenes and hence is a critical requirement to build intelligent systems for driver assistance and self-driving. Most of the existing datasets for text detection and recognition comprise still images and are mostly compiled keeping text in mind. This paper introduces a new ”RoadText-1K” dataset for text in driving videos. The dataset is 20 times larger than the existing largest dataset for text in videos. Our dataset comprises 1000 video clips of driving without any bias towards text and with annotations for text bounding boxes and transcriptions in every frame. State of the art methods for text detection,
recognition and tracking are evaluated on the new dataset and the results signify the challenges in unconstrained driving videos compared to existing datasets. This suggests that RoadText-1K is suited for research and development of reading systems, robust enough to be incorporated into more complex downstream tasks like driver assistance and self-driving. The dataset can be found at http://cvit.iiit.ac.in/research/ projects/cvit-projects/roadtext-1k |
||||
| Address | Paris; Francia; ??? | ||||
| 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 | ICRA | ||
| Notes | DAG; 600.121; 600.129 | Approved | no | ||
| Call Number | Admin @ si @ RMG2020 | Serial | 3400 | ||
| Permanent link to this record | |||||
| Author | Vacit Oguz Yazici; Abel Gonzalez-Garcia; Arnau Ramisa; Bartlomiej Twardowski; Joost Van de Weijer | ||||
| Title | Orderless Recurrent Models for Multi-label Classification | Type | Conference Article | ||
| Year | 2020 | Publication | 33rd IEEE Conference on Computer Vision and Pattern Recognition | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | Recurrent neural networks (RNN) are popular for many computer vision tasks, including multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered for the multi-label classification task. Current approaches sort labels according to their frequency, typically ordering them in either rare-first or frequent-first. These imposed orderings do not take into account that the natural order to generate the labels can change for each image, e.g.\ first the dominant object before summing up the smaller objects in the image. Therefore, in this paper, we propose ways to dynamically order the ground truth labels with the predicted label sequence. This allows for the faster training of more optimal LSTM models for multi-label classification. Analysis evidences that our method does not suffer from duplicate generation, something which is common for other models. Furthermore, it outperforms other CNN-RNN models, and we show that a standard architecture of an image encoder and language decoder trained with our proposed loss obtains the state-of-the-art results on the challenging MS-COCO, WIDER Attribute and PA-100K and competitive results on NUS-WIDE. | ||||
| 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 | CVPR | ||
| Notes | LAMP; 600.109; 601.309; 600.141; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ YGR2020 | Serial | 3408 | ||
| Permanent link to this record | |||||
| Author | M. Ivasic-Kos; M. Pobar; Jordi Gonzalez | ||||
| Title | Active Player Detection in Handball Videos Using Optical Flow and STIPs Based Measures | Type | Conference Article | ||
| Year | 2019 | Publication | 13th International Conference on Signal Processing and Communication Systems | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | In handball videos recorded during the training, multiple players are present in the scene at the same time. Although they all might move and interact, not all players contribute to the currently relevant exercise nor practice the given handball techniques. The goal of this experiment is to automatically determine players on training footage that perform given handball techniques and are therefore considered active. It is a very challenging task for which a precise object detector is needed that can handle cluttered scenes with poor illumination, with many players present in different sizes and distances from the camera, partially occluded, moving fast. To determine which of the detected players are active, additional information is needed about the level of player activity. Since many handball actions are characterized by considerable changes in speed, position, and variations in the player's appearance, we propose using spatio-temporal interest points (STIPs) and optical flow (OF). Therefore, we propose an active player detection method combining the YOLO object detector and two activity measures based on STIPs and OF. The performance of the proposed method and activity measures are evaluated on a custom handball video dataset acquired during handball training lessons. | ||||
| Address | Gold Coast; Australia; December 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 | ICSPCS2 | ||
| Notes | ISE; 600.098; 600.119 | Approved | no | ||
| Call Number | Admin @ si @ IPG2019 | Serial | 3415 | ||
| Permanent link to this record | |||||
| Author | Xialei Liu; Chenshen Wu; Mikel Menta; Luis Herranz; Bogdan Raducanu; Andrew Bagdanov; Shangling Jui; Joost Van de Weijer | ||||
| Title | Generative Feature Replay for Class-Incremental Learning | Type | Conference Article | ||
| Year | 2020 | Publication | CLVISION – Workshop on Continual Learning in Computer Vision | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the task-ID is unknown at inference time. The imbalance between old and new classes typically results in a bias of the network towards the newest ones. This imbalance problem can either be addressed by storing exemplars from previous tasks, or by using image replay methods. However, the latter can only be applied to toy datasets since image generation for complex datasets is a hard problem.
We propose a solution to the imbalance problem based on generative feature replay which does not require any exemplars. To do this, we split the network into two parts: a feature extractor and a classifier. To prevent forgetting, we combine generative feature replay in the classifier with feature distillation in the feature extractor. Through feature generation, our method reduces the complexity of generative replay and prevents the imbalance problem. Our approach is computationally efficient and scalable to large datasets. Experiments confirm that our approach achieves state-of-the-art results on CIFAR-100 and ImageNet, while requiring only a fraction of the storage needed for exemplar-based continual learning |
||||
| 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 | CVPRW | ||
| Notes | LAMP; 601.309; 602.200; 600.141; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ LWM2020 | Serial | 3419 | ||
| Permanent link to this record | |||||
| Author | Raul Gomez; Jaume Gibert; Lluis Gomez; Dimosthenis Karatzas | ||||
| Title | Location Sensitive Image Retrieval and Tagging | Type | Conference Article | ||
| Year | 2020 | Publication | 16th European Conference on Computer Vision | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | People from different parts of the globe describe objects and concepts in distinct manners. Visual appearance can thus vary across different geographic locations, which makes location a relevant contextual information when analysing visual data. In this work, we address the task of image retrieval related to a given tag conditioned on a certain location on Earth. We present LocSens, a model that learns to rank triplets of images, tags and coordinates by plausibility, and two training strategies to balance the location influence in the final ranking. LocSens learns to fuse textual and location information of multimodal queries to retrieve related images at different levels of location granularity, and successfully utilizes location information to improve image tagging. | ||||
| Address | Virtual; August 2020 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | ECCV | ||
| Notes | DAG; 600.121; 600.129 | Approved | no | ||
| Call Number | Admin @ si @ GGG2020b | Serial | 3420 | ||
| Permanent link to this record | |||||
| Author | Yaxing Wang; Abel Gonzalez-Garcia; David Berga; Luis Herranz; Fahad Shahbaz Khan; Joost Van de Weijer | ||||
| Title | MineGAN: effective knowledge transfer from GANs to target domains with few images | Type | Conference Article | ||
| Year | 2020 | Publication | 33rd IEEE Conference on Computer Vision and Pattern Recognition | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | One of the attractive characteristics of deep neural networks is their ability to transfer knowledge obtained in one domain to other related domains. As a result, high-quality networks can be trained in domains with relatively little training data. This property has been extensively studied for discriminative networks but has received significantly less attention for generative models. Given the often enormous effort required to train GANs, both computationally as well as in the dataset collection, the re-use of pretrained GANs is a desirable objective. We propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs. This is done using a miner network that identifies which part of the generative distribution of each pretrained GAN outputs samples closest to the target domain. Mining effectively steers GAN sampling towards suitable regions of the latent space, which facilitates the posterior finetuning and avoids pathologies of other methods such as mode collapse and lack of flexibility. We perform experiments on several complex datasets using various GAN architectures (BigGAN, Progressive GAN) and show that the proposed method, called MineGAN, effectively transfers knowledge to domains with few target images, outperforming existing methods. In addition, MineGAN can successfully transfer knowledge from multiple pretrained GANs. | ||||
| 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 | LAMP; 600.109; 600.141; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ WGB2020 | Serial | 3421 | ||
| Permanent link to this record | |||||
| Author | Lu Yu; Bartlomiej Twardowski; Xialei Liu; Luis Herranz; Kai Wang; Yongmai Cheng; Shangling Jui; Joost Van de Weijer | ||||
| Title | Semantic Drift Compensation for Class-Incremental Learning of Embeddings | Type | Conference Article | ||
| Year | 2020 | Publication | 33rd IEEE Conference on Computer Vision and Pattern Recognition | Abbreviated Journal | |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this setting, networks suffer from catastrophic forgetting which refers to the drastic drop in performance on previous tasks. The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes. Embedding networks have the advantage that new classes can be naturally included into the network without adding new weights. Therefore, we study incremental learning for embedding networks. In addition, we propose a new method to estimate the drift, called semantic drift, of features and compensate for it without the need of any exemplars. We approximate the drift of previous tasks based on the drift that is experienced by current task data. We perform experiments on fine-grained datasets, CIFAR100 and ImageNet-Subset. We demonstrate that embedding networks suffer significantly less from catastrophic forgetting. We outperform existing methods which do not require exemplars and obtain competitive results compared to methods which store exemplars. Furthermore, we show that our proposed SDC when combined with existing methods to prevent forgetting consistently improves results. | ||||
| 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 | LAMP; 600.141; 601.309; 602.200; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ YTL2020 | Serial | 3422 | ||
| Permanent link to this record | |||||
| Author | Xiangyang Li; Luis Herranz; Shuqiang Jiang | ||||
| Title | Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition | Type | Journal | ||
| Year | 2020 | Publication | ACM Transactions on Data Science | Abbreviated Journal | ACM |
| Volume | Issue | Pages |
|||
| Keywords | |||||
| Abstract | In recent years, convolutional neural networks (CNNs) have achieved impressive performance for various visual recognition scenarios. CNNs trained on large labeled datasets can not only obtain significant performance on most challenging benchmarks but also provide powerful representations, which can be used to a wide range of other tasks. However, the requirement of massive amounts of data to train deep neural networks is a major drawback of these models, as the data available is usually limited or imbalanced. Fine-tuning (FT) is an effective way to transfer knowledge learned in a source dataset to a target task. In this paper, we introduce and systematically investigate several factors that influence the performance of fine-tuning for visual recognition. These factors include parameters for the retraining procedure (e.g., the initial learning rate of fine-tuning), the distribution of the source and target data (e.g., the number of categories in the source dataset, the distance between the source and target datasets) and so on. We quantitatively and qualitatively analyze these factors, evaluate their influence, and present many empirical observations. The results reveal insights into what fine-tuning changes CNN parameters and provide useful and evidence-backed intuitions about how to implement fine-tuning for computer vision tasks. | ||||
| 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 @ LHJ2020 | Serial | 3423 | ||
| Permanent link to this record | |||||