| Home | [111–120] << 121 122 123 124 125 126 127 128 129 130 >> [131–140] |
|
| Records | |||||
|---|---|---|---|---|---|
| Author | 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 | Hassan Ahmed Sial; Ramon Baldrich; Maria Vanrell; Dimitris Samaras | ||||
| Title |
Light Direction and Color Estimation from Single Image with Deep Regression | Type | Conference Article | ||
| Year | 2020 | Publication | London Imaging Conference | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | We present a method to estimate the direction and color of the scene light source from a single image. Our method is based on two main ideas: (a) we use a new synthetic dataset with strong shadow effects with similar constraints to the SID dataset; (b) we define a deep architecture trained on the mentioned dataset to estimate the direction and color of the scene light source. Apart from showing good performance on synthetic images, we additionally propose a preliminary procedure to obtain light positions of the Multi-Illumination dataset, and, in this way, we also prove that our trained model achieves good performance when it is applied to real scenes. | ||||
| Address | Virtual; September 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 | LIM | ||
| Notes | CIC; 600.118; 600.140; | Approved | no | ||
| Call Number | Admin @ si @ SBV2020 | Serial | 3460 | ||
| Permanent link to this record | |||||
| Author | Hamdi Dibeklioglu; Albert Ali Salah; Theo Gevers | ||||
| Title |
Like Father, Like Son: Facial Expression Dynamics for Kinship Verification | Type | Conference Article | ||
| Year | 2013 | Publication | 15th IEEE International Conference on Computer Vision | Abbreviated Journal | |
| Volume | Issue | Pages | 1497-1504 | ||
| Keywords | |||||
| Abstract | Kinship verification from facial appearance is a difficult problem. This paper explores the possibility of employing facial expression dynamics in this problem. By using features that describe facial dynamics and spatio-temporal appearance over smile expressions, we show that it is possible to improve the state of the art in this problem, and verify that it is indeed possible to recognize kinship by resemblance of facial expressions. The proposed method is tested on different kin relationships. On the average, 72.89% verification accuracy is achieved on spontaneous smiles. | ||||
| Address | Sydney | ||||
| 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 | ALTRES;ISE | Approved | no | ||
| Call Number | Admin @ si @ DSG2013 | Serial | 2366 | ||
| Permanent link to this record | |||||
| Author | C. Alejandro Parraga; Jordi Roca; Dimosthenis Karatzas; Sophie Wuerger | ||||
| Title |
Limitations of visual gamma corrections in LCD displays | Type | Journal Article | ||
| Year | 2014 | Publication | Displays | Abbreviated Journal | Dis |
| Volume | 35 | Issue | 5 | Pages | 227–239 |
| Keywords | Display calibration; Psychophysics; Perceptual; Visual gamma correction; Luminance matching; Observer-based calibration | ||||
| Abstract | A method for estimating the non-linear gamma transfer function of liquid–crystal displays (LCDs) without the need of a photometric measurement device was described by Xiao et al. (2011) [1]. It relies on observer’s judgments of visual luminance by presenting eight half-tone patterns with luminances from 1/9 to 8/9 of the maximum value of each colour channel. These half-tone patterns were distributed over the screen both over the vertical and horizontal viewing axes. We conducted a series of photometric and psychophysical measurements (consisting in the simultaneous presentation of half-tone patterns in each trial) to evaluate whether the angular dependency of the light generated by three different LCD technologies would bias the results of these gamma transfer function estimations. Our results show that there are significant differences between the gamma transfer functions measured and produced by observers at different viewing angles. We suggest appropriate modifications to the Xiao et al. paradigm to counterbalance these artefacts which also have the advantage of shortening the amount of time spent in collecting the psychophysical measurements. | ||||
| 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 | CIC; DAG; 600.052; 600.077; 600.074 | Approved | no | ||
| Call Number | Admin @ si @ PRK2014 | Serial | 2511 | ||
| Permanent link to this record | |||||
| Author | Oriol Ramos Terrades; Ernest Valveny | ||||
| Title |
Line Detection Using Ridgelets Transform for Graphic Symbol Representation | Type | Miscellaneous | ||
| Year | 2003 | Publication | In Pattern Recognition and Image Analysis, Lecture Notes in Computer Science 2652:829–837 | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | |||||
| Address | Springer-Verlag | ||||
| 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 | DAG | Approved | no | ||
| Call Number | DAG @ dag @ RaV2003a | Serial | 403 | ||
| Permanent link to this record | |||||
| Author | Enric Marti; Jordi Regincos; Juan Jose Villanueva; Jaime Lopez-Krahe | ||||
| Title |
Line drawing interpretation as polyhedral objects to man-machine interaction in CAD systems | Type | Book Chapter | ||
| Year | 1994 | Publication | Advances in Pattern Recognition and Image Analysis, | Abbreviated Journal | |
| Volume | Issue | Pages | 158-169 | ||
| Keywords | |||||
| Abstract | |||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | World Scientific Pub. | Place of Publication | Editor | ||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 981-02-1872-9 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | IAM;ISE | Approved | no | ||
| Call Number | IAM @ iam @ MRL1994 | Serial | 1609 | ||
| Permanent link to this record | |||||
| Author | Oriol Ramos Terrades | ||||
| Title |
Linear Combination of Multiresolution Descriptors: Application to Graphics Recognition | Type | Book Whole | ||
| Year | 2006 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC & Universite Nancy 2 | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | |||||
| Address | |||||
| Corporate Author | Thesis | Ph.D. thesis | |||
| Publisher | Place of Publication | Editor | Salvatore Antoine Tabbone;Ernest Valveny | ||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | DAG | Approved | no | ||
| Call Number | DAG @ dag @ Ram2006 | Serial | 713 | ||
| Permanent link to this record | |||||
| Author | Fernando Vilariño; Panagiota Spyridonos; Jordi Vitria; C. Malagelada; Petia Radeva | ||||
| Title |
Linear Radial Patterns Characterization for Automatic Detection of Tonic Intestinal Contractions | Type | Book Chapter | ||
| Year | 2006 | Publication | 11th Iberoamerican Congress on Pattern Recognition | Abbreviated Journal | |
| Volume | 4225 | Issue | Pages | 178–187 | |
| Keywords | |||||
| Abstract | This work tackles the categorization of general linear radial patterns by means of the valleys and ridges detection and the use of descriptors of directional information, which are provided by steerable filters in different regions of the image. We successfully apply our proposal in the specific case of automatic detection of tonic contractions in video capsule endoscopy, which represent a paradigmatic example of linear radial patterns. | ||||
| Address | Cancun (Mexico) | ||||
| Corporate Author | Thesis | ||||
| Publisher | Springer Verlag | Place of Publication | Berlin Heidelberg | Editor | .F. Mart ́ınez-Trinidad et al |
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | 800 | Expedition | Conference | ||
| Notes | MV;OR;MILAB;SIAI | Approved | no | ||
| Call Number | BCNPCL @ bcnpcl @ VSV2006c; IAM @ iam @ VSB2006f | Serial | 728 | ||
| Permanent link to this record | |||||
| Author | Armin Mehri; Parichehr Behjati Ardakani; Angel Sappa | ||||
| Title |
LiNet: A Lightweight Network for Image Super Resolution | Type | Conference Article | ||
| Year | 2021 | Publication | 25th International Conference on Pattern Recognition | Abbreviated Journal | |
| Volume | Issue | Pages | 7196-7202 | ||
| Keywords | |||||
| Abstract | This paper proposes a new lightweight network, LiNet, that enhancing technical efficiency in lightweight super resolution and operating approximately like very large and costly networks in terms of number of network parameters and operations. The proposed architecture allows the network to learn more abstract properties by avoiding low-level information via multiple links. LiNet introduces a Compact Dense Module, which contains set of inner and outer blocks, to efficiently extract meaningful information, to better leverage multi-level representations before upsampling stage, and to allow an efficient information and gradient flow within the network. Experiments on benchmark datasets show that the proposed LiNet achieves favorable performance against lightweight state-of-the-art methods. | ||||
| Address | Virtual; January 2021 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | MSIAU; 600.130; 600.122 | Approved | no | ||
| Call Number | Admin @ si @ MAS2021a | Serial | 3583 | ||
| Permanent link to this record | |||||
| Author | X. Binefa; J.M. Sanchez; Petia Radeva; Jordi Vitria | ||||
| Title |
Linking Visual Cues and Semantic Terms Under Specific Digital Video Domains. | Type | Miscellaneous | ||
| Year | 2000 | Publication | Journal of Visual Languages and Computing, 11(3):253–271. | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | |||||
| 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 | OR;MILAB;MV | Approved | no | ||
| Call Number | BCNPCL @ bcnpcl @ BRS2000 | Serial | 337 | ||
| Permanent link to this record | |||||
| Author | Ozan Caglayan; Walid Aransa; Adrien Bardet; Mercedes Garcia-Martinez; Fethi Bougares; Loic Barrault; Marc Masana; Luis Herranz; Joost Van de Weijer | ||||
| Title |
LIUM-CVC Submissions for WMT17 Multimodal Translation Task | Type | Conference Article | ||
| Year | 2017 | Publication | 2nd Conference on Machine Translation | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | This paper describes the monomodal and multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation. We mainly explored two multimodal architectures where either global visual features or convolutional feature maps are integrated in order to benefit from visual context. Our final systems ranked first for both En-De and En-Fr language pairs according to the automatic evaluation metrics METEOR and BLEU. | ||||
| 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 | WMT | ||
| Notes | LAMP; 600.106; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ CAB2017 | Serial | 3035 | ||
| Permanent link to this record | |||||
| Author | Ozan Caglayan; Adrien Bardet; Fethi Bougares; Loic Barrault; Kai Wang; Marc Masana; Luis Herranz; Joost Van de Weijer | ||||
| Title |
LIUM-CVC Submissions for WMT18 Multimodal Translation Task | Type | Conference Article | ||
| Year | 2018 | Publication | 3rd Conference on Machine Translation | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation. This year we propose several modifications to our previou multimodal attention architecture in order to better integrate convolutional features and refine them using encoder-side information. Our final constrained submissions
ranked first for English→French and second for English→German language pairs among the constrained submissions according to the automatic evaluation metric METEOR. |
||||
| Address | Brussels; Belgium; October 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 | WMT | ||
| Notes | LAMP; 600.106; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ CBB2018 | Serial | 3240 | ||
| Permanent link to this record | |||||
| Author | J.M. Sanchez; X. Binefa; Jordi Vitria; Petia Radeva | ||||
| Title |
Local Analysis for Scene Break Detection Applied to TV Commercials Recognition. | Type | Miscellaneous | ||
| Year | 1999 | Publication | Visual information and information systems, 237–244, Springer– Verlag. | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | |||||
| 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 | OR;MILAB;MV | Approved | no | ||
| Call Number | BCNPCL @ bcnpcl @ SBV1999 | Serial | 27 | ||
| Permanent link to this record | |||||
| Author | Patricia Marquez; Debora Gil; R.Mester; Aura Hernandez-Sabate | ||||
| Title |
Local Analysis of Confidence Measures for Optical Flow Quality Evaluation | Type | Conference Article | ||
| Year | 2014 | Publication | 9th International Conference on Computer Vision Theory and Applications | Abbreviated Journal | |
| Volume | 3 | Issue | Pages | 450-457 | |
| Keywords | Optical Flow; Confidence Measure; Performance Evaluation. | ||||
| Abstract | Optical Flow (OF) techniques facing the complexity of real sequences have been developed in the last years. Even using the most appropriate technique for our specific problem, at some points the output flow might fail to achieve the minimum error required for the system. Confidence measures computed from either input data or OF output should discard those points where OF is not accurate enough for its further use. It follows that evaluating the capabilities of a confidence measure for bounding OF error is as important as the definition
itself. In this paper we analyze different confidence measures and point out their advantages and limitations for their use in real world settings. We also explore the agreement with current tools for their evaluation of confidence measures performance. |
||||
| Address | Lisboa; January 2014 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | VISAPP | ||
| Notes | IAM; ADAS; 600.044; 600.060; 600.057; 601.145; 600.076; 600.075 | Approved | no | ||
| Call Number | Admin @ si @ MGM2014 | Serial | 2432 | ||
| Permanent link to this record | |||||
| Author | B. Moghaddam; David Guillamet; Jordi Vitria | ||||
| Title |
Local Appearance-Based Models using High-Order Statistics of Image Features | Type | Miscellaneous | ||
| Year | 2003 | Publication | Mitsubishi Electrical Reasearch Lab Technical Report | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | |||||
| 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 | OR;MV | Approved | no | ||
| Call Number | BCNPCL @ bcnpcl @ TR2003-85 | Serial | 396 | ||
| Permanent link to this record | |||||