Home [131–140] << 141 142 143 144 145 146 147 148 149 150 >> [151–160]
List View
 | 
Citations
 | 
Details
   web
Records
Author (up) Marc Castello; Jordi Gonzalez; Ariel Amato; Pau Baiget; Carles Fernandez; Josep M. Gonfaus; Ramon Mollineda; Marco Pedersoli; Nicolas Perez de la Blanca; Xavier Roca
Title Exploiting Multimodal Interaction Techniques for Video-Surveillance Type Book Chapter
Year 2013 Publication Multimodal Interaction in Image and Video Applications Intelligent Systems Reference Library Abbreviated Journal
Volume 48 Issue 8 Pages 135-151
Keywords
Abstract In this paper we present an example of a video surveillance application that exploits Multimodal Interactive (MI) technologies. The main objective of the so-called VID-Hum prototype was to develop a cognitive artificial system for both the detection and description of a particular set of human behaviours arising from real-world events. The main procedure of the prototype described in this chapter entails: (i) adaptation, since the system adapts itself to the most common behaviours (qualitative data) inferred from tracking (quantitative data) thus being able to recognize abnormal behaviors; (ii) feedback, since an advanced interface based on Natural Language understanding allows end-users the communicationwith the prototype by means of conceptual sentences; and (iii) multimodality, since a virtual avatar has been designed to describe what is happening in the scene, based on those textual interpretations generated by the prototype. Thus, the MI methodology has provided an adequate framework for all these cooperating processes.
Address
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1868-4394 ISBN 978-3-642-35931-6 Medium
Area Expedition Conference
Notes ISE; 605.203; 600.049 Approved no
Call Number CGA2013 Serial 2222
Permanent link to this record
 
 
Author (up) Marc Masana
Title Lifelong Learning of Neural Networks: Detecting Novelty and Adapting to New Domains without Forgetting Type Book Whole
Year 2020 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Computer vision has gone through considerable changes in the last decade as neural networks have come into common use. As available computational capabilities have grown, neural networks have achieved breakthroughs in many computer vision tasks, and have even surpassed human performance in others. With accuracy being so high, focus has shifted to other issues and challenges. One research direction that saw a notable increase in interest is on lifelong learning systems. Such systems should be capable of efficiently performing tasks, identifying and learning new ones, and should moreover be able to deploy smaller versions of themselves which are experts on specific tasks. In this thesis, we contribute to research on lifelong learning and address the compression and adaptation of networks to small target domains, the incremental learning of networks faced with a variety of tasks, and finally the detection of out-of-distribution samples at inference time.

We explore how knowledge can be transferred from large pretrained models to more task-specific networks capable of running on smaller devices by extracting the most relevant information. Using a pretrained model provides more robust representations and a more stable initialization when learning a smaller task, which leads to higher performance and is known as domain adaptation. However, those models are too large for certain applications that need to be deployed on devices with limited memory and computational capacity. In this thesis we show that, after performing domain adaptation, some learned activations barely contribute to the predictions of the model. Therefore, we propose to apply network compression based on low-rank matrix decomposition using the activation statistics. This results in a significant reduction of the model size and the computational cost.

Like human intelligence, machine intelligence aims to have the ability to learn and remember knowledge. However, when a trained neural network is presented with learning a new task, it ends up forgetting previous ones. This is known as catastrophic forgetting and its avoidance is studied in continual learning. The work presented in this thesis extensively surveys continual learning techniques and presents an approach to avoid catastrophic forgetting in sequential task learning scenarios. Our technique is based on using ternary masks in order to update a network to new tasks, reusing the knowledge of previous ones while not forgetting anything about them. In contrast to earlier work, our masks are applied to the activations of each layer instead of the weights. This considerably reduces the number of parameters to be added for each new task. Furthermore, the analysis on a wide range of work on incremental learning without access to the task-ID, provides insight on current state-of-the-art approaches that focus on avoiding catastrophic forgetting by using regularization, rehearsal of previous tasks from a small memory, or compensating the task-recency bias.

Neural networks trained with a cross-entropy loss force the outputs of the model to tend toward a one-hot encoded vector. This leads to models being too overly confident when presented with images or classes that were not present in the training distribution. The capacity of a system to be aware of the boundaries of the learned tasks and identify anomalies or classes which have not been learned yet is key to lifelong learning and autonomous systems. In this thesis, we present a metric learning approach to out-of-distribution detection that learns the task at hand on an embedding space.
Address
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Joost Van de Weijer;Andrew Bagdanov
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-121011-9-5 Medium
Area Expedition Conference
Notes LAMP; 600.120 Approved no
Call Number Admin @ si @ Mas20 Serial 3481
Permanent link to this record
 
 
Author (up) Marc Masana; Bartlomiej Twardowski; Joost Van de Weijer
Title On Class Orderings for Incremental Learning Type Conference Article
Year 2020 Publication ICML Workshop on Continual Learning Abbreviated Journal
Volume Issue Pages
Keywords
Abstract The influence of class orderings in the evaluation of incremental learning has received very little attention. In this paper, we investigate the impact of class orderings for incrementally learned classifiers. We propose a method to compute various orderings for a dataset. The orderings are derived by simulated annealing optimization from the confusion matrix and reflect different incremental learning scenarios, including maximally and minimally confusing tasks. We evaluate a wide range of state-of-the-art incremental learning methods on the proposed orderings. Results show that orderings can have a significant impact on performance and the ranking of the methods.
Address Virtual; July 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 ICMLW
Notes LAMP; 600.120 Approved no
Call Number Admin @ si @ MTW2020 Serial 3505
Permanent link to this record
 
 
Author (up) Marc Masana; Idoia Ruiz; Joan Serrat; Joost Van de Weijer; Antonio Lopez
Title Metric Learning for Novelty and Anomaly Detection Type Conference Article
Year 2018 Publication 29th British Machine Vision Conference Abbreviated Journal
Volume Issue Pages
Keywords
Abstract When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so too confidently. The capability to detect out-of-distribution images is therefore crucial for many real-world applications. We divide out-of-distribution detection between novelty detection ---images of classes which are not in the training set but are related to those---, and anomaly detection ---images with classes which are unrelated to the training set. By related we mean they contain the same type of objects, like digits in MNIST and SVHN. Most existing work has focused on anomaly detection, and has addressed this problem considering networks trained with the cross-entropy loss. Differently from them, we propose to use metric learning which does not have the drawback of the softmax layer (inherent to cross-entropy methods), which forces the network to divide its prediction power over the learned classes. We perform extensive experiments and evaluate both novelty and anomaly detection, even in a relevant application such as traffic sign recognition, obtaining comparable or better results than previous works.
Address Newcastle; uk; September 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 BMVC
Notes LAMP; ADAS; 601.305; 600.124; 600.106; 602.200; 600.120; 600.118 Approved no
Call Number Admin @ si @ MRS2018 Serial 3156
Permanent link to this record
 
 
Author (up) Marc Masana; Joost Van de Weijer; Andrew Bagdanov
Title On-the-fly Network pruning for object detection Type Conference Article
Year 2016 Publication International conference on learning representations Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Object detection with deep neural networks is often performed by passing a few
thousand candidate bounding boxes through a deep neural network for each image.
These bounding boxes are highly correlated since they originate from the same
image. In this paper we investigate how to exploit feature occurrence at the image scale to prune the neural network which is subsequently applied to all bounding boxes. We show that removing units which have near-zero activation in the image allows us to significantly reduce the number of parameters in the network. Results on the PASCAL 2007 Object Detection Challenge demonstrate that up to 40% of units in some fully-connected layers can be entirely eliminated with little change in the detection result.
Address Puerto Rico; May 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 ICLR
Notes LAMP; 600.068; 600.106; 600.079 Approved no
Call Number Admin @ si @MWB2016 Serial 2758
Permanent link to this record
 
 
Author (up) Marc Masana; Joost Van de Weijer; Luis Herranz;Andrew Bagdanov; Jose Manuel Alvarez
Title Domain-adaptive deep network compression Type Conference Article
Year 2017 Publication 17th IEEE International Conference on Computer Vision Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Deep Neural Networks trained on large datasets can be easily transferred to new domains with far fewer labeled examples by a process called fine-tuning. This has the advantage that representations learned in the large source domain can be exploited on smaller target domains. However, networks designed to be optimal for the source task are often prohibitively large for the target task. In this work we address the compression of networks after domain transfer.
We focus on compression algorithms based on low-rank matrix decomposition. Existing methods base compression solely on learned network weights and ignore the statistics of network activations. We show that domain transfer leads to large shifts in network activations and that it is desirable to take this into account when compressing.
We demonstrate that considering activation statistics when compressing weights leads to a rank-constrained regression problem with a closed-form solution. Because our method takes into account the target domain, it can more optimally
remove the redundancy in the weights. Experiments show that our Domain Adaptive Low Rank (DALR) method significantly outperforms existing low-rank compression techniques. With our approach, the fc6 layer of VGG19 can be compressed more than 4x more than using truncated SVD alone – with only a minor or no loss in accuracy. When applied to domain-transferred networks it allows for compression down to only 5-20% of the original number of parameters with only a minor drop in performance.
Address Venice; Italy; October 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 ICCV
Notes LAMP; 601.305; 600.106; 600.120 Approved no
Call Number Admin @ si @ Serial 3034
Permanent link to this record
 
 
Author (up) Marc Masana; Tinne Tuytelaars; Joost Van de Weijer
Title Ternary Feature Masks: zero-forgetting for task-incremental learning Type Conference Article
Year 2021 Publication 34th IEEE Conference on Computer Vision and Pattern Recognition Workshops Abbreviated Journal
Volume Issue Pages 3565-3574
Keywords
Abstract We propose an approach without any forgetting to continual learning for the task-aware regime, where at inference the task-label is known. By using ternary masks we can upgrade a model to new tasks, reusing knowledge from previous tasks while not forgetting anything about them. Using masks prevents both catastrophic forgetting and backward transfer. We argue -- and show experimentally -- that avoiding the former largely compensates for the lack of the latter, which is rarely observed in practice. In contrast to earlier works, our masks are applied to the features (activations) of each layer instead of the weights. This considerably reduces the number of mask parameters for each new task; with more than three orders of magnitude for most networks. The encoding of the ternary masks into two bits per feature creates very little overhead to the network, avoiding scalability issues. To allow already learned features to adapt to the current task without changing the behavior of these features for previous tasks, we introduce task-specific feature normalization. Extensive experiments on several finegrained datasets and ImageNet show that our method outperforms current state-of-the-art while reducing memory overhead in comparison to weight-based approaches.
Address Virtual; June 2021
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference CVPRW
Notes LAMP; 600.120 Approved no
Call Number Admin @ si @ MTW2021 Serial 3565
Permanent link to this record
 
 
Author (up) Marc Masana; Xialei Liu; Bartlomiej Twardowski; Mikel Menta; Andrew Bagdanov; Joost Van de Weijer
Title Class-incremental learning: survey and performance evaluation Type Journal Article
Year 2022 Publication IEEE Transactions on Pattern Analysis and Machine Intelligence Abbreviated Journal TPAMI
Volume Issue Pages
Keywords
Abstract For future learning systems incremental learning is desirable, because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored -- also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neural networks has seen explosive growth in recent years. Initial work focused on task incremental learning, where a task-ID is provided at inference time. Recently we have seen a shift towards class-incremental learning where the learner must classify at inference time between all classes seen in previous tasks without recourse to a task-ID. In this paper, we provide a complete survey of existing methods for incremental learning, and in particular we perform an extensive experimental evaluation on twelve class-incremental methods. We consider several new experimental scenarios, including a comparison of class-incremental methods on multiple large-scale datasets, investigation into small and large domain shifts, and comparison on various network architectures.
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; 600.120 Approved no
Call Number Admin @ si @ MLT2022 Serial 3538
Permanent link to this record
 
 
Author (up) Marc Oliu; Ciprian Corneanu; Kamal Nasrollahi; Olegs Nikisins; Sergio Escalera; Yunlian Sun; Haiqing Li; Zhenan Sun; Thomas B. Moeslund; Modris Greitans
Title Improved RGB-D-T based Face Recognition Type Journal Article
Year 2016 Publication IET Biometrics Abbreviated Journal BIO
Volume 5 Issue 4 Pages 297 - 303
Keywords
Abstract Reliable facial recognition systems are of crucial importance in various applications from entertainment to security. Thanks to the deep-learning concepts introduced in the field, a significant improvement in the performance of the unimodal facial recognition systems has been observed in the recent years. At the same time a multimodal facial recognition is a promising approach. This study combines the latest successes in both directions by applying deep learning convolutional neural networks (CNN) to the multimodal RGB, depth, and thermal (RGB-D-T) based facial recognition problem outperforming previously published results. Furthermore, a late fusion of the CNN-based recognition block with various hand-crafted features (local binary patterns, histograms of oriented gradients, Haar-like rectangular features, histograms of Gabor ordinal measures) is introduced, demonstrating even better recognition performance on a benchmark RGB-D-T database. The obtained results in this study show that the classical engineered features and CNN-based features can complement each other for recognition purposes.
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;MILAB; Approved no
Call Number Admin @ si @ OCN2016 Serial 2854
Permanent link to this record
 
 
Author (up) Marc Oliu; Ciprian Corneanu; Laszlo A. Jeni; Jeffrey F. Cohn; Takeo Kanade; Sergio Escalera
Title Continuous Supervised Descent Method for Facial Landmark Localisation Type Conference Article
Year 2016 Publication 13th Asian Conference on Computer Vision Abbreviated Journal
Volume 10112 Issue Pages 121-135
Keywords
Abstract Recent methods for facial landmark location perform well on close-to-frontal faces but have problems in generalising to large head rotations. In order to address this issue we propose a second order linear regression method that is both compact and robust against strong rotations. We provide a closed form solution, making the method fast to train. We test the method’s performance on two challenging datasets. The first has been intensely used by the community. The second has been specially generated from a well known 3D face dataset. It is considerably more challenging, including a high diversity of rotations and more samples than any other existing public dataset. The proposed method is compared against state-of-the-art approaches, including RCPR, CGPRT, LBF, CFSS, and GSDM. Results upon both datasets show that the proposed method offers state-of-the-art performance on near frontal view data, improves state-of-the-art methods on more challenging head rotation problems and keeps a compact model size.
Address Taipei; Taiwan; November 2016
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 ACCV
Notes HuPBA;MILAB; Approved no
Call Number Admin @ si @ OCJ2016 Serial 2838
Permanent link to this record
 
 
Author (up) Marc Oliu; Javier Selva; Sergio Escalera
Title Folded Recurrent Neural Networks for Future Video Prediction Type Conference Article
Year 2018 Publication 15th European Conference on Computer Vision Abbreviated Journal
Volume 11218 Issue Pages 745-761
Keywords
Abstract Future video prediction is an ill-posed Computer Vision problem that recently received much attention. Its main challenges are the high variability in video content, the propagation of errors through time, and the non-specificity of the future frames: given a sequence of past frames there is a continuous distribution of possible futures. This work introduces bijective Gated Recurrent Units, a double mapping between the input and output of a GRU layer. This allows for recurrent auto-encoders with state sharing between encoder and decoder, stratifying the sequence representation and helping to prevent capacity problems. We show how with this topology only the encoder or decoder needs to be applied for input encoding and prediction, respectively. This reduces the computational cost and avoids re-encoding the predictions when generating a sequence of frames, mitigating the propagation of errors. Furthermore, it is possible to remove layers from an already trained model, giving an insight to the role performed by each layer and making the model more explainable. We evaluate our approach on three video datasets, outperforming state of the art prediction results on MMNIST and UCF101, and obtaining competitive results on KTH with 2 and 3 times less memory usage and computational cost than the best scored approach.
Address Munich; September 2018
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 ECCV
Notes HUPBA; no menciona Approved no
Call Number Admin @ si @ OSE2018 Serial 3204
Permanent link to this record
 
 
Author (up) Marc Oliu; Sarah Adel Bargal; Stan Sclaroff; Xavier Baro; Sergio Escalera
Title Multi-varied Cumulative Alignment for Domain Adaptation Type Conference Article
Year 2022 Publication 6th International Conference on Image Analysis and Processing Abbreviated Journal
Volume 13232 Issue Pages 324–334
Keywords Domain Adaptation; Computer vision; Neural networks
Abstract Domain Adaptation methods can be classified into two basic families of approaches: non-parametric and parametric. Non-parametric approaches depend on statistical indicators such as feature covariances to minimize the domain shift. Non-parametric approaches tend to be fast to compute and require no additional parameters, but they are unable to leverage probability density functions with complex internal structures. Parametric approaches, on the other hand, use models of the probability distributions as surrogates in minimizing the domain shift, but they require additional trainable parameters to model these distributions. In this work, we propose a new statistical approach to minimizing the domain shift based on stochastically projecting and evaluating the cumulative density function in both domains. As with non-parametric approaches, there are no additional trainable parameters. As with parametric approaches, the internal structure of both domains’ probability distributions is considered, thus leveraging a higher amount of information when reducing the domain shift. Evaluation on standard datasets used for Domain Adaptation shows better performance of the proposed model compared to non-parametric approaches while being competitive with parametric ones. (Code available at: https://github.com/moliusimon/mca).
Address Indonesia; October 2022
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 ICIAP
Notes HuPBA; no menciona Approved no
Call Number Admin @ si @ OAS2022 Serial 3777
Permanent link to this record
 
 
Author (up) Marc Serra
Title Estimating Intrinsic Images from Physical and Categorical Color Cues Type Report
Year 2010 Publication CVC Technical Report Abbreviated Journal
Volume 151 Issue Pages
Keywords
Abstract
Address
Corporate Author Thesis Master's 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 CIC Approved no
Call Number Admin @ si @ Ser2010 Serial 1345
Permanent link to this record
 
 
Author (up) Marc Serra
Title Modeling, estimation and evaluation of intrinsic images considering color information Type Book Whole
Year 2015 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Image values are the result of a combination of visual information coming from multiple sources. Recovering information from the multiple factors thatproduced an image seems a hard and ill-posed problem. However, it is important to observe that humans develop the ability to interpret images and recognize and isolate specific physical properties of the scene.

Images describing a single physical characteristic of an scene are called intrinsic images. These images would benefit most computer vision tasks which are often affected by the multiple complex effects that are usually found in natural images (e.g. cast shadows, specularities, interreflections...).

In this thesis we analyze the problem of intrinsic image estimation from different perspectives, including the theoretical formulation of the problem, the visual cues that can be used to estimate the intrinsic components and the evaluation mechanisms of the problem.
Address September 2015
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Robert Benavente;Olivier Penacchio
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-943427-4-5 Medium
Area Expedition Conference
Notes CIC; 600.074 Approved no
Call Number Admin @ si @ Ser2015 Serial 2688
Permanent link to this record
 
 
Author (up) Marc Serra; Olivier Penacchio; Robert Benavente; Maria Vanrell
Title Names and Shades of Color for Intrinsic Image Estimation Type Conference Article
Year 2012 Publication 25th IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal
Volume Issue Pages 278-285
Keywords
Abstract In the last years, intrinsic image decomposition has gained attention. Most of the state-of-the-art methods are based on the assumption that reflectance changes come along with strong image edges. Recently, user intervention in the recovery problem has proved to be a remarkable source of improvement. In this paper, we propose a novel approach that aims to overcome the shortcomings of pure edge-based methods by introducing strong surface descriptors, such as the color-name descriptor which introduces high-level considerations resembling top-down intervention. We also use a second surface descriptor, termed color-shade, which allows us to include physical considerations derived from the image formation model capturing gradual color surface variations. Both color cues are combined by means of a Markov Random Field. The method is quantitatively tested on the MIT ground truth dataset using different error metrics, achieving state-of-the-art performance.
Address Providence, Rhode Island
Corporate Author Thesis
Publisher IEEE Xplore Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1063-6919 ISBN 978-1-4673-1226-4 Medium
Area Expedition Conference CVPR
Notes CIC Approved no
Call Number Admin @ si @ SPB2012 Serial 2026
Permanent link to this record