toggle visibility Search & Display Options
Select All    Deselect All [1–10] << 11 12 13 14 15 >>
List View
 | 
Citations
 | 
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 Pattern Recognition Letters Abbreviated Journal PRL  
  Volume 150 Issue Pages (down) 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 Alex Gomez-Villa; Adrian Martin; Javier Vazquez; Marcelo Bertalmio; Jesus Malo edit  url
doi  openurl
  Title On the synthesis of visual illusions using deep generative models Type Journal Article
  Year 2022 Publication Journal of Vision Abbreviated Journal JOV  
  Volume 22(8) Issue 2 Pages (down) 1-18  
  Keywords  
  Abstract Visual illusions expand our understanding of the visual system by imposing constraints in the models in two different ways: i) visual illusions for humans should induce equivalent illusions in the model, and ii) illusions synthesized from the model should be compelling for human viewers too. These constraints are alternative strategies to find good vision models. Following the first research strategy, recent studies have shown that artificial neural network architectures also have human-like illusory percepts when stimulated with classical hand-crafted stimuli designed to fool humans. In this work we focus on the second (less explored) strategy: we propose a framework to synthesize new visual illusions using the optimization abilities of current automatic differentiation techniques. The proposed framework can be used with classical vision models as well as with more recent artificial neural network architectures. This framework, validated by psychophysical experiments, can be used to study the difference between a vision model and the actual human perception and to optimize the vision model to decrease this difference.  
  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; 600.161; 611.007 Approved no  
  Call Number Admin @ si @ GMV2022 Serial 3682  
Permanent link to this record
 
 
Author Xiangyang Li; Luis Herranz; Shuqiang Jiang edit   pdf
url  openurl
  Title Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition Type Journal
  Year 2020 Publication ACM Transactions on Data Science Abbreviated Journal ACM  
  Volume Issue Pages (down)  
  Keywords  
  Abstract In recent years, convolutional neural networks (CNNs) have achieved impressive performance for various visual recognition scenarios. CNNs trained on large labeled datasets can not only obtain significant performance on most challenging benchmarks but also provide powerful representations, which can be used to a wide range of other tasks. However, the requirement of massive amounts of data to train deep neural networks is a major drawback of these models, as the data available is usually limited or imbalanced. Fine-tuning (FT) is an effective way to transfer knowledge learned in a source dataset to a target task. In this paper, we introduce and systematically investigate several factors that influence the performance of fine-tuning for visual recognition. These factors include parameters for the retraining procedure (e.g., the initial learning rate of fine-tuning), the distribution of the source and target data (e.g., the number of categories in the source dataset, the distance between the source and target datasets) and so on. We quantitatively and qualitatively analyze these factors, evaluate their influence, and present many empirical observations. The results reveal insights into what fine-tuning changes CNN parameters and provide useful and evidence-backed intuitions about how to implement fine-tuning for computer vision tasks.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes LAMP; 600.141; 600.120 Approved no  
  Call Number Admin @ si @ LHJ2020 Serial 3423  
Permanent link to this record
 
 
Author Marc Masana; Xialei Liu; Bartlomiej Twardowski; Mikel Menta; Andrew Bagdanov; Joost Van de Weijer edit   pdf
doi  openurl
  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 (down)  
  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 Lu Yu; Xialei Liu; Joost Van de Weijer edit   pdf
doi  openurl
  Title Self-Training for Class-Incremental Semantic Segmentation Type Journal Article
  Year 2022 Publication IEEE Transactions on Neural Networks and Learning Systems Abbreviated Journal TNNLS  
  Volume Issue Pages (down)  
  Keywords Class-incremental learning; Self-training; Semantic segmentation.  
  Abstract In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned knowledge. To address this problem, we propose to apply a self-training approach that leverages unlabeled data, which is used for rehearsal of previous knowledge. Specifically, we first learn a temporary model for the current task, and then, pseudo labels for the unlabeled data are computed by fusing information from the old model of the previous task and the current temporary model. In addition, conflict reduction is proposed to resolve the conflicts of pseudo labels generated from both the old and temporary models. We show that maximizing self-entropy can further improve results by smoothing the overconfident predictions. Interestingly, in the experiments, we show that the auxiliary data can be different from the training data and that even general-purpose, but diverse auxiliary data can lead to large performance gains. The experiments demonstrate the state-of-the-art results: obtaining a relative gain of up to 114% on Pascal-VOC 2012 and 8.5% on the more challenging ADE20K compared to previous state-of-the-art 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; 611.008; Approved no  
  Call Number Admin @ si @ YLW2022 Serial 3745  
Permanent link to this record
Select All    Deselect All [1–10] << 11 12 13 14 15 >>
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: