| Home | [191–200] << 201 202 203 204 205 206 207 208 209 210 >> [211–220] |
|
| Records | |||||
|---|---|---|---|---|---|
| Author | Mohammed Al Rawi; Dimosthenis Karatzas | ||||
| Title | On the Labeling Correctness in Computer Vision Datasets | Type | Conference Article | ||
| Year | 2018 | Publication | Proceedings of the Workshop on Interactive Adaptive Learning, co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Image datasets have heavily been used to build computer vision systems.
These datasets are either manually or automatically labeled, which is a problem as both labeling methods are prone to errors. To investigate this problem, we use a majority voting ensemble that combines the results from several Convolutional Neural Networks (CNNs). Majority voting ensembles not only enhance the overall performance, but can also be used to estimate the confidence level of each sample. We also examined Softmax as another form to estimate posterior probability. We have designed various experiments with a range of different ensembles built from one or different, or temporal/snapshot CNNs, which have been trained multiple times stochastically. We analyzed CIFAR10, CIFAR100, EMNIST, and SVHN datasets and we found quite a few incorrect labels, both in the training and testing sets. We also present detailed confidence analysis on these datasets and we found that the ensemble is better than the Softmax when used estimate the per-sample confidence. This work thus proposes an approach that can be used to scrutinize and verify the labeling of computer vision datasets, which can later be applied to weakly/semi-supervised learning. We propose a measure, based on the Odds-Ratio, to quantify how many of these incorrectly classified labels are actually incorrectly labeled and how many of these are confusing. The proposed methods are easily scalable to larger datasets, like ImageNet, LSUN and SUN, as each CNN instance is trained for 60 epochs; or even faster, by implementing a temporal (snapshot) ensemble. |
||||
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 | ECML-PKDDW | ||
| Notes | DAG; 600.121; 600.129 | Approved | no | ||
| Call Number | Admin @ si @ RaK2018 | Serial | 3144 | ||
| Permanent link to this record | |||||
| Author | Xavier Soria; Angel Sappa; Riad I. Hammoud | ||||
| Title | Wide-Band Color Imagery Restoration for RGB-NIR Single Sensor Images | Type | Journal Article | ||
| Year | 2018 | Publication | Sensors | Abbreviated Journal | SENS |
| Volume | 18 | Issue | 7 | Pages | 2059 |
| Keywords | RGB-NIR sensor; multispectral imaging; deep learning; CNNs | ||||
| Abstract | Multi-spectral RGB-NIR sensors have become ubiquitous in recent years. These sensors allow the visible and near-infrared spectral bands of a given scene to be captured at the same time. With such cameras, the acquired imagery has a compromised RGB color representation due to near-infrared bands (700–1100 nm) cross-talking with the visible bands (400–700 nm).
This paper proposes two deep learning-based architectures to recover the full RGB color images, thus removing the NIR information from the visible bands. The proposed approaches directly restore the high-resolution RGB image by means of convolutional neural networks. They are evaluated with several outdoor images; both architectures reach a similar performance when evaluated in different scenarios and using different similarity metrics. Both of them improve the state of the art approaches. |
||||
| 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 | ADAS; MSIAU; 600.086; 600.130; 600.122; 600.118 | Approved | no | ||
| Call Number | Admin @ si @ SSH2018 | Serial | 3145 | ||
| Permanent link to this record | |||||
| Author | Oscar Argudo; Marc Comino; Antonio Chica; Carlos Andujar; Felipe Lumbreras | ||||
| Title | Segmentation of aerial images for plausible detail synthesis | Type | Journal Article | ||
| Year | 2018 | Publication | Computers & Graphics | Abbreviated Journal | CG |
| Volume | 71 | Issue | Pages | 23-34 | |
| Keywords | Terrain editing; Detail synthesis; Vegetation synthesis; Terrain rendering; Image segmentation | ||||
| Abstract | The visual enrichment of digital terrain models with plausible synthetic detail requires the segmentation of aerial images into a suitable collection of categories. In this paper we present a complete pipeline for segmenting high-resolution aerial images into a user-defined set of categories distinguishing e.g. terrain, sand, snow, water, and different types of vegetation. This segmentation-for-synthesis problem implies that per-pixel categories must be established according to the algorithms chosen for rendering the synthetic detail. This precludes the definition of a universal set of labels and hinders the construction of large training sets. Since artists might choose to add new categories on the fly, the whole pipeline must be robust against unbalanced datasets, and fast on both training and inference. Under these constraints, we analyze the contribution of common per-pixel descriptors, and compare the performance of state-of-the-art supervised learning algorithms. We report the findings of two user studies. The first one was conducted to analyze human accuracy when manually labeling aerial images. The second user study compares detailed terrains built using different segmentation strategies, including official land cover maps. These studies demonstrate that our approach can be used to turn digital elevation models into fully-featured, detailed terrains with minimal authoring efforts. | ||||
| 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 | 0097-8493 | ISBN | Medium | ||
| Area | Expedition | Conference | |||
| Notes | MSIAU; 600.086; 600.118 | Approved | no | ||
| Call Number | Admin @ si @ ACC2018 | Serial | 3147 | ||
| Permanent link to this record | |||||
| Author | Xim Cerda-Company; Xavier Otazu; Nilai Sallent; C. Alejandro Parraga | ||||
| Title | The effect of luminance differences on color assimilation | Type | Journal Article | ||
| Year | 2018 | Publication | Journal of Vision | Abbreviated Journal | JV |
| Volume | 18 | Issue | 11 | Pages | 10-10 |
| Keywords | |||||
| Abstract | The color appearance of a surface depends on the color of its surroundings (inducers). When the perceived color shifts towards that of the surroundings, the effect is called “color assimilation” and when it shifts away from the surroundings it is called “color contrast.” There is also evidence that the phenomenon depends on the spatial configuration of the inducer, e.g., uniform surrounds tend to induce color contrast and striped surrounds tend to induce color assimilation. However, previous work found that striped surrounds under certain conditions do not induce color assimilation but induce color contrast (or do not induce anything at all), suggesting that luminance differences and high spatial frequencies could be key factors in color assimilation. Here we present a new psychophysical study of color assimilation where we assessed the contribution of luminance differences (between the target and its surround) present in striped stimuli. Our results show that luminance differences are key factors in color assimilation for stimuli varying along the s axis of MacLeod-Boynton color space, but not for stimuli varying along the l axis. This asymmetry suggests that koniocellular neural mechanisms responsible for color assimilation only contribute when there is a luminance difference, supporting the idea that mutual-inhibition has a major role in color induction. | ||||
| 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 | NEUROBIT; 600.120; 600.128 | Approved | no | ||
| Call Number | Admin @ si @ COS2018 | Serial | 3148 | ||
| Permanent link to this record | |||||
| Author | Domicele Jonauskaite; Nele Dael; C. Alejandro Parraga; Laetitia Chevre; Alejandro Garcia Sanchez; Christine Mohr | ||||
| Title | Stripping #The Dress: The importance of contextual information on inter-individual differences in colour perception | Type | Journal Article | ||
| Year | 2018 | Publication | Psychological Research | Abbreviated Journal | PSYCHO R |
| Volume | Issue | Pages | 1-15 | ||
| Keywords | |||||
| Abstract | In 2015, a picture of a Dress (henceforth the Dress) triggered popular and scientific interest; some reported seeing the Dress in white and gold (W&G) and others in blue and black (B&B). We aimed to describe the phenomenon and investigate the role of contextualization. Few days after the Dress had appeared on the Internet, we projected it to 240 students on two large screens in the classroom. Participants reported seeing the Dress in B&B (48%), W&G (38%), or blue and brown (B&Br; 7%). Amongst numerous socio-demographic variables, we only observed that W&G viewers were most likely to have always seen the Dress as W&G. In the laboratory, we tested how much contextual information is necessary for the phenomenon to occur. Fifty-seven participants selected colours most precisely matching predominant colours of parts or the full Dress. We presented, in this order, small squares (a), vertical strips (b), and the full Dress (c). We found that (1) B&B, B&Br, and W&G viewers had selected colours differing in lightness and chroma levels for contextualized images only (b, c conditions) and hue for fully contextualized condition only (c) and (2) B&B viewers selected colours most closely matching displayed colours of the Dress. Thus, the Dress phenomenon emerges due to inter-individual differences in subjectively perceived lightness, chroma, and hue, at least when all aspects of the picture need to be integrated. Our results support the previous conclusions that contextual information is key to colour perception; it should be important to understand how this actually happens. | ||||
| 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 | NEUROBIT; no proj | Approved | no | ||
| Call Number | Admin @ si @ JDP2018 | Serial | 3149 | ||
| Permanent link to this record | |||||
| Author | Thanh Nam Le; Muhammad Muzzamil Luqman; Anjan Dutta; Pierre Heroux; Christophe Rigaud; Clement Guerin; Pasquale Foggia; Jean Christophe Burie; Jean Marc Ogier; Josep Llados; Sebastien Adam | ||||
| Title | Subgraph spotting in graph representations of comic book images | Type | Journal Article | ||
| Year | 2018 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
| Volume | 112 | Issue | Pages | 118-124 | |
| Keywords | Attributed graph; Region adjacency graph; Graph matching; Graph isomorphism; Subgraph isomorphism; Subgraph spotting; Graph indexing; Graph retrieval; Query by example; Dataset and comic book images | ||||
| Abstract | Graph-based representations are the most powerful data structures for extracting, representing and preserving the structural information of underlying data. Subgraph spotting is an interesting research problem, especially for studying and investigating the structural information based content-based image retrieval (CBIR) and query by example (QBE) in image databases. In this paper we address the problem of lack of freely available ground-truthed datasets for subgraph spotting and present a new dataset for subgraph spotting in graph representations of comic book images (SSGCI) with its ground-truth and evaluation protocol. Experimental results of two state-of-the-art methods of subgraph spotting are presented on the new SSGCI dataset. | ||||
| 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 | DAG; 600.097; 600.121 | Approved | no | ||
| Call Number | Admin @ si @ LLD2018 | Serial | 3150 | ||
| Permanent link to this record | |||||
| Author | Fernando Vilariño; Dimosthenis Karatzas; Alberto Valcarce | ||||
| Title | The Library Living Lab Barcelona: A participative approach to technology as an enabling factor for innovation in cultural spaces | Type | Journal | ||
| Year | 2018 | Publication | Technology Innovation Management Review | 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 | DAG; MV; 600.097; 600.121; 600.129;SIAI | Approved | no | ||
| Call Number | Admin @ si @ VKV2018a | Serial | 3153 | ||
| Permanent link to this record | |||||
| Author | Muhammad Anwer Rao; Fahad Shahbaz Khan; Joost Van de Weijer; Matthieu Molinier; Jorma Laaksonen | ||||
| Title | Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification | Type | Journal Article | ||
| Year | 2018 | Publication | ISPRS Journal of Photogrammetry and Remote Sensing | Abbreviated Journal | ISPRS J |
| Volume | 138 | Issue | Pages | 74-85 | |
| Keywords | Remote sensing; Deep learning; Scene classification; Local Binary Patterns; Texture analysis | ||||
| Abstract | Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless statistical distribution of local features. However, most recent approaches to texture recognition and remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The de facto practice when learning these CNN models is to use RGB patches as input with training performed on large amounts of labeled data (ImageNet). In this paper, we show that Local Binary Patterns (LBP) encoded CNN models, codenamed TEX-Nets, trained using mapped coded images with explicit LBP based texture information provide complementary information to the standard RGB deep models. Additionally, two deep architectures, namely early and late fusion, are investigated to combine the texture and color information. To the best of our knowledge, we are the first to investigate Binary Patterns encoded CNNs and different deep network fusion architectures for texture recognition and remote sensing scene classification. We perform comprehensive experiments on four texture recognition datasets and four remote sensing scene classification benchmarks: UC-Merced with 21 scene categories, WHU-RS19 with 19 scene classes, RSSCN7 with 7 categories and the recently introduced large scale aerial image dataset (AID) with 30 aerial scene types. We demonstrate that TEX-Nets provide complementary information to standard RGB deep model of the same network architecture. Our late fusion TEX-Net architecture always improves the overall performance compared to the standard RGB network on both recognition problems. Furthermore, our final combination leads to consistent improvement over the state-of-the-art for remote sensing scene | ||||
| 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; 600.109; 600.106; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ RKW2018 | Serial | 3158 | ||
| Permanent link to this record | |||||
| Author | Xialei Liu; Marc Masana; Luis Herranz; Joost Van de Weijer; Antonio Lopez; Andrew Bagdanov | ||||
| Title | Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting | Type | Conference Article | ||
| Year | 2018 | Publication | 24th International Conference on Pattern Recognition | Abbreviated Journal | |
| Volume | Issue | Pages | 2262-2268 | ||
| Keywords | |||||
| Abstract | In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the network parameters. This reparameterization takes the form of
a factorized rotation of parameter space which, when used in conjunction with Elastic Weight Consolidation (which assumes a diagonal Fisher Information Matrix), leads to significantly better performance on lifelong learning of sequential tasks. Experimental results on the MNIST, CIFAR-100, CUB-200 and Stanford-40 datasets demonstrate that we significantly improve the results of standard elastic weight consolidation, and that we obtain competitive results when compared to the state-of-the-art in lifelong learning without forgetting. |
||||
| 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 | ICPR | ||
| Notes | LAMP; ADAS; 601.305; 601.109; 600.124; 600.106; 602.200; 600.120; 600.118 | Approved | no | ||
| Call Number | Admin @ si @ LMH2018 | Serial | 3160 | ||
| Permanent link to this record | |||||
| Author | Jorge Bernal; Aymeric Histace; Marc Masana; Quentin Angermann; Cristina Sanchez Montes; Cristina Rodriguez de Miguel; Maroua Hammami; Ana Garcia Rodriguez; Henry Cordova; Olivier Romain; Gloria Fernandez Esparrach; Xavier Dray; F. Javier Sanchez | ||||
| Title | GTCreator: a flexible annotation tool for image-based datasets | Type | Journal Article | ||
| Year | 2019 | Publication | International Journal of Computer Assisted Radiology and Surgery | Abbreviated Journal | IJCAR |
| Volume | 14 | Issue | 2 | Pages | 191–201 |
| Keywords | Annotation tool; Validation Framework; Benchmark; Colonoscopy; Evaluation | ||||
| Abstract | Abstract Purpose: Methodology evaluation for decision support systems for health is a time consuming-task. To assess performance of polyp detection
methods in colonoscopy videos, clinicians have to deal with the annotation of thousands of images. Current existing tools could be improved in terms of exibility and ease of use. Methods:We introduce GTCreator, a exible annotation tool for providing image and text annotations to image-based datasets. It keeps the main basic functionalities of other similar tools while extending other capabilities such as allowing multiple annotators to work simultaneously on the same task or enhanced dataset browsing and easy annotation transfer aiming to speed up annotation processes in large datasets. Results: The comparison with other similar tools shows that GTCreator allows to obtain fast and precise annotation of image datasets, being the only one which offers full annotation editing and browsing capabilites. Conclusions: Our proposed annotation tool has been proven to be efficient for large image dataset annota- tion, as well as showing potential of use in other stages of method evaluation such as experimental setup or results analysis. |
||||
| 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 | MV; 600.096; 600.109; 600.119; 601.305 | Approved | no | ||
| Call Number | Admin @ si @ BHM2019 | Serial | 3163 | ||
| Permanent link to this record | |||||
| Author | Cristina Sanchez Montes; F. Javier Sanchez; Jorge Bernal; Henry Cordova; Maria Lopez Ceron; Miriam Cuatrecasas; Cristina Rodriguez de Miguel; Ana Garcia Rodriguez; Rodrigo Garces Duran; Maria Pellise; Josep Llach; Gloria Fernandez Esparrach | ||||
| Title | Computer-aided Prediction of Polyp Histology on White-Light Colonoscopy using Surface Pattern Analysis | Type | Journal Article | ||
| Year | 2019 | Publication | Endoscopy | Abbreviated Journal | END |
| Volume | 51 | Issue | 3 | Pages | 261-265 |
| Keywords | |||||
| Abstract | Background and study aims: To evaluate a new computational histology prediction system based on colorectal polyp textural surface patterns using high definition white light images.
Patients and methods: Textural elements (textons) were characterized according to their contrast with respect to the surface, shape and number of bifurcations, assuming that dysplastic polyps are associated with highly contrasted, large tubular patterns with some degree of bifurcation. Computer-aided diagnosis (CAD) was compared with pathological diagnosis and the diagnosis by the endoscopists using Kudo and NICE classification. Results: Images of 225 polyps were evaluated (142 dysplastic and 83 non-dysplastic). CAD system correctly classified 205 (91.1%) polyps, 131/142 (92.3%) dysplastic and 74/83 (89.2%) non-dysplastic. For the subgroup of 100 diminutive (<5 mm) polyps, CAD correctly classified 87 (87%) polyps, 43/50 (86%) dysplastic and 44/50 (88%) non-dysplastic. There were not statistically significant differences in polyp histology prediction based on CAD system and on endoscopist assessment. Conclusion: A computer vision system based on the characterization of the polyp surface in the white light accurately predicts colorectal polyp histology. |
||||
| 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 | MV; 600.096; 600.119; 600.075 | Approved | no | ||
| Call Number | Admin @ si @ SSB2019 | Serial | 3164 | ||
| Permanent link to this record | |||||
| Author | Juan Ignacio Toledo; Manuel Carbonell; Alicia Fornes; Josep Llados | ||||
| Title | Information Extraction from Historical Handwritten Document Images with a Context-aware Neural Model | Type | Journal Article | ||
| Year | 2019 | Publication | Pattern Recognition | Abbreviated Journal | PR |
| Volume | 86 | Issue | Pages | 27-36 | |
| Keywords | Document image analysis; Handwritten documents; Named entity recognition; Deep neural networks | ||||
| Abstract | Many historical manuscripts that hold trustworthy memories of the past societies contain information organized in a structured layout (e.g. census, birth or marriage records). The precious information stored in these documents cannot be effectively used nor accessed without costly annotation efforts. The transcription driven by the semantic categories of words is crucial for the subsequent access. In this paper we describe an approach to extract information from structured historical handwritten text images and build a knowledge representation for the extraction of meaning out of historical data. The method extracts information, such as named entities, without the need of an intermediate transcription step, thanks to the incorporation of context information through language models. Our system has two variants, the first one is based on bigrams, whereas the second one is based on recurrent neural networks. Concretely, our second architecture integrates a Convolutional Neural Network to model visual information from word images together with a Bidirecitonal Long Short Term Memory network to model the relation among the words. This integrated sequential approach is able to extract more information than just the semantic category (e.g. a semantic category can be associated to a person in a record). Our system is generic, it deals with out-of-vocabulary words by design, and it can be applied to structured handwritten texts from different domains. The method has been validated with the ICDAR IEHHR competition protocol, outperforming the existing approaches. | ||||
| 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 | DAG; 600.097; 601.311; 603.057; 600.084; 600.140; 600.121 | Approved | no | ||
| Call Number | Admin @ si @ TCF2019 | Serial | 3166 | ||
| Permanent link to this record | |||||
| Author | Alicia Fornes; Bart Lamiroy | ||||
| Title | Graphics Recognition, Current Trends and Evolutions | Type | Book Whole | ||
| Year | 2018 | Publication | Graphics Recognition, Current Trends and Evolutions | Abbreviated Journal | |
| Volume | 11009 | Issue | Pages | ||
| Keywords | |||||
| Abstract | This book constitutes the thoroughly refereed post-conference proceedings of the 12th International Workshop on Graphics Recognition, GREC 2017, held in Kyoto, Japan, in November 2017.
The 10 revised full papers presented were carefully reviewed and selected from 14 initial submissions. They contain both classical and emerging topics of graphics rcognition, namely analysis and detection of diagrams, search and classification, optical music recognition, interpretation of engineering drawings and maps. |
||||
| Address |
|||||
| Corporate Author | Thesis | ||||
| Publisher | Springer International Publishing | Place of Publication | Editor | ||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 978-3-030-02283-9 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | DAG; 600.121 | Approved | no | ||
| Call Number | Admin @ si @ FoL2018 | Serial | 3171 | ||
| Permanent link to this record | |||||
| Author | Katerine Diaz; Jesus Martinez del Rincon; Marçal Rusiñol; Aura Hernandez-Sabate | ||||
| Title | Feature Extraction by Using Dual-Generalized Discriminative Common Vectors | Type | Journal Article | ||
| Year | 2019 | Publication | Journal of Mathematical Imaging and Vision | Abbreviated Journal | JMIV |
| Volume | 61 | Issue | 3 | Pages | 331-351 |
| Keywords | Online feature extraction; Generalized discriminative common vectors; Dual learning; Incremental learning; Decremental learning | ||||
| Abstract | In this paper, a dual online subspace-based learning method called dual-generalized discriminative common vectors (Dual-GDCV) is presented. The method extends incremental GDCV by exploiting simultaneously both the concepts of incremental and decremental learning for supervised feature extraction and classification. Our methodology is able to update the feature representation space without recalculating the full projection or accessing the previously processed training data. It allows both adding information and removing unnecessary data from a knowledge base in an efficient way, while retaining the previously acquired knowledge. The proposed method has been theoretically proved and empirically validated in six standard face recognition and classification datasets, under two scenarios: (1) removing and adding samples of existent classes, and (2) removing and adding new classes to a classification problem. Results show a considerable computational gain without compromising the accuracy of the model in comparison with both batch methodologies and other state-of-art adaptive methods. | ||||
| 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 | DAG; ADAS; 600.084; 600.118; 600.121; 600.129 | Approved | no | ||
| Call Number | Admin @ si @ DRR2019 | Serial | 3172 | ||
| Permanent link to this record | |||||
| Author | Y. Patel; Lluis Gomez; Raul Gomez; Marçal Rusiñol; Dimosthenis Karatzas; C.V. Jawahar | ||||
| Title | TextTopicNet-Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces | Type | Miscellaneous | ||
| Year | 2018 | Publication | Arxiv | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such datasets requires a tremendous amount of human effort and annotations are limited to popular set of classes. As an alternative, learning visual features by designing auxiliary tasks which make use of freely available self-supervision has become increasingly popular in the computer vision community.
In this paper, we put forward an idea to take advantage of multi-modal context to provide self-supervision for the training of computer vision algorithms. We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration. More specifically we use popular text embedding techniques to provide the self-supervision for the training of deep CNN. |
||||
| 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 | DAG; 600.084; 601.338; 600.121 | Approved | no | ||
| Call Number | Admin @ si @ PGG2018 | Serial | 3177 | ||
| Permanent link to this record | |||||