toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Carola Figueroa Flores; David Berga; Joost Van de Weijer; Bogdan Raducanu edit   pdf
url  openurl
  Title Saliency for free: Saliency prediction as a side-effect of object recognition Type Journal Article
  Year 2021 Publication (down) Pattern Recognition Letters Abbreviated Journal PRL  
  Volume 150 Issue Pages 1-7  
  Keywords Saliency maps; Unsupervised learning; Object recognition  
  Abstract Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects instead of the background. So far, computational methods for saliency estimation required the explicit generation of a saliency map, process which is usually achieved via eyetracking experiments on still images. This is a tedious process that needs to be repeated for each new dataset. In the current paper, we demonstrate that is possible to automatically generate saliency maps without ground-truth. In our approach, saliency maps are learned as a side effect of object recognition. Extensive experiments carried out on both real and synthetic datasets demonstrated that our approach is able to generate accurate saliency maps, achieving competitive results when compared with supervised 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 LAMP; 600.147; 600.120 Approved no  
  Call Number Admin @ si @ FBW2021 Serial 3559  
Permanent link to this record
 

 
Author Kai Wang; Joost Van de Weijer; Luis Herranz edit   pdf
url  openurl
  Title ACAE-REMIND for online continual learning with compressed feature replay Type Journal Article
  Year 2021 Publication (down) Pattern Recognition Letters Abbreviated Journal PRL  
  Volume 150 Issue Pages 122-129  
  Keywords online continual learning; autoencoders; vector quantization  
  Abstract Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior results than image replay, while requiring less memory. Quantized exemplars can further reduce the memory usage. However, a drawback of these methods is that they use a fixed (or very intransigent) backbone network. This significantly limits the learning of representations that can discriminate between all tasks. To address this problem, we propose an auxiliary classifier auto-encoder (ACAE) module for feature replay at intermediate layers with high compression rates. The reduced memory footprint per image allows us to save more exemplars for replay. In our experiments, we conduct task-agnostic evaluation under online continual learning setting and get state-of-the-art performance on ImageNet-Subset, CIFAR100 and CIFAR10 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 LAMP; 600.147; 601.379; 600.120; 600.141 Approved no  
  Call Number Admin @ si @ WWH2021 Serial 3575  
Permanent link to this record
 

 
Author Francesco Ciompi; Oriol Pujol; Petia Radeva edit  doi
openurl 
  Title ECOC-DRF: Discriminative random fields based on error correcting output codes Type Journal Article
  Year 2014 Publication (down) Pattern Recognition Abbreviated Journal PR  
  Volume 47 Issue 6 Pages 2193-2204  
  Keywords Discriminative random fields; Error-correcting output codes; Multi-class classification; Graphical models  
  Abstract We present ECOC-DRF, a framework where potential functions for Discriminative Random Fields are formulated as an ensemble of classifiers. We introduce the label trick, a technique to express transitions in the pairwise potential as meta-classes. This allows to independently learn any possible transition between labels without assuming any pre-defined model. The Error Correcting Output Codes matrix is used as ensemble framework for the combination of margin classifiers. We apply ECOC-DRF to a large set of classification problems, covering synthetic, natural and medical images for binary and multi-class cases, outperforming state-of-the art in almost all the experiments.  
  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; HuPBA; MILAB; 605.203; 600.046; 601.043; 600.079 Approved no  
  Call Number Admin @ si @ CPR2014b Serial 2470  
Permanent link to this record
 

 
Author Svebor Karaman; Giuseppe Lisanti; Andrew Bagdanov; Alberto del Bimbo edit   pdf
doi  openurl
  Title Leveraging local neighborhood topology for large scale person re-identification Type Journal Article
  Year 2014 Publication (down) Pattern Recognition Abbreviated Journal PR  
  Volume 47 Issue 12 Pages 3767–3778  
  Keywords Re-identification; Conditional random field; Semi-supervised; ETHZ; CAVIAR; 3DPeS; CMV100  
  Abstract In this paper we describe a semi-supervised approach to person re-identification that combines discriminative models of person identity with a Conditional Random Field (CRF) to exploit the local manifold approximation induced by the nearest neighbor graph in feature space. The linear discriminative models learned on few gallery images provides coarse separation of probe images into identities, while a graph topology defined by distances between all person images in feature space leverages local support for label propagation in the CRF. We evaluate our approach using multiple scenarios on several publicly available datasets, where the number of identities varies from 28 to 191 and the number of images ranges between 1003 and 36 171. We demonstrate that the discriminative model and the CRF are complementary and that the combination of both leads to significant improvement over state-of-the-art approaches. We further demonstrate how the performance of our approach improves with increasing test data and also with increasing amounts of additional unlabeled data.  
  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; 601.240; 600.079 Approved no  
  Call Number Admin @ si @ KLB2014a Serial 2522  
Permanent link to this record
 

 
Author Carola Figueroa Flores; Abel Gonzalez-Garcia; Joost Van de Weijer; Bogdan Raducanu edit   pdf
url  openurl
  Title Saliency for fine-grained object recognition in domains with scarce training data Type Journal Article
  Year 2019 Publication (down) Pattern Recognition Abbreviated Journal PR  
  Volume 94 Issue Pages 62-73  
  Keywords  
  Abstract This paper investigates the role of saliency to improve the classification accuracy of a Convolutional Neural Network (CNN) for the case when scarce training data is available. Our approach consists in adding a saliency branch to an existing CNN architecture which is used to modulate the standard bottom-up visual features from the original image input, acting as an attentional mechanism that guides the feature extraction process. The main aim of the proposed approach is to enable the effective training of a fine-grained recognition model with limited training samples and to improve the performance on the task, thereby alleviating the need to annotate a large dataset. The vast majority of saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline. Our proposed pipeline allows to evaluate saliency methods for the high-level task of object recognition. We perform extensive experiments on various fine-grained datasets (Flowers, Birds, Cars, and Dogs) under different conditions and show that saliency can considerably improve the network’s performance, especially for the case of scarce training data. Furthermore, our experiments show that saliency methods that obtain improved saliency maps (as measured by traditional saliency benchmarks) also translate to saliency methods that yield improved performance gains when applied in an object recognition pipeline.  
  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; OR; 600.109; 600.141; 600.120 Approved no  
  Call Number Admin @ si @ FGW2019 Serial 3264  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: