| |
Records |
Links |
|
Author |
Carola Figueroa Flores; Abel Gonzalez-Garcia; Joost Van de Weijer; Bogdan Raducanu |
|
| |
Title |
Saliency for fine-grained object recognition in domains with scarce training data |
Type  |
Journal Article |
| |
Year |
2019 |
Publication |
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 |
| |
|
| |
|
Author |
Xialei Liu; Joost Van de Weijer; Andrew Bagdanov |
|
| |
Title |
Exploiting Unlabeled Data in CNNs by Self-Supervised Learning to Rank |
Type |
Journal Article |
| |
Year |
2019 |
Publication |
IEEE Transactions on Pattern Analysis and Machine Intelligence |
Abbreviated Journal |
TPAMI |
|
| |
Volume |
41 |
Issue |
8 |
Pages |
1862-1878 |
|
| |
Keywords |
Task analysis;Training;Image quality;Visualization;Uncertainty;Labeling;Neural networks;Learning from rankings;image quality assessment;crowd counting;active learning |
|
| |
Abstract |
For many applications the collection of labeled data is expensive laborious. Exploitation of unlabeled data during training is thus a long pursued objective of machine learning. Self-supervised learning addresses this by positing an auxiliary task (different, but related to the supervised task) for which data is abundantly available. In this paper, we show how ranking can be used as a proxy task for some regression problems. As another contribution, we propose an efficient backpropagation technique for Siamese networks which prevents the redundant computation introduced by the multi-branch network architecture. We apply our framework to two regression problems: Image Quality Assessment (IQA) and Crowd Counting. For both we show how to automatically generate ranked image sets from unlabeled data. Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results for both IQA and crowd counting. In addition, we show that measuring network uncertainty on the self-supervised proxy task is a good measure of informativeness of unlabeled data. This can be used to drive an algorithm for active learning and we show that this reduces labeling effort by up to 50 percent. |
|
| |
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 |
LWB2019 |
Serial |
3267 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Aitor Alvarez-Gila; Adrian Galdran; Estibaliz Garrote; Joost Van de Weijer |
|
| |
Title |
Self-supervised blur detection from synthetically blurred scenes |
Type |
Journal Article |
| |
Year |
2019 |
Publication |
Image and Vision Computing |
Abbreviated Journal |
IMAVIS |
|
| |
Volume |
92 |
Issue |
|
Pages |
103804 |
|
| |
Keywords |
|
|
| |
Abstract |
Blur detection aims at segmenting the blurred areas of a given image. Recent deep learning-based methods approach this problem by learning an end-to-end mapping between the blurred input and a binary mask representing the localization of its blurred areas. Nevertheless, the effectiveness of such deep models is limited due to the scarcity of datasets annotated in terms of blur segmentation, as blur annotation is labor intensive. In this work, we bypass the need for such annotated datasets for end-to-end learning, and instead rely on object proposals and a model for blur generation in order to produce a dataset of synthetically blurred images. This allows us to perform self-supervised learning over the generated image and ground truth blur mask pairs using CNNs, defining a framework that can be employed in purely self-supervised, weakly supervised or semi-supervised configurations. Interestingly, experimental results of such setups over the largest blur segmentation datasets available show that this approach achieves state of the art results in blur segmentation, even without ever observing any real blurred image. |
|
| |
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; 600.120 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ AGG2019 |
Serial |
3301 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Fei Yang; Yongmei Cheng; Joost Van de Weijer; Mikhail Mozerov |
|
| |
Title |
Improved Discrete Optical Flow Estimation With Triple Image Matching Cost |
Type |
Journal Article |
| |
Year |
2020 |
Publication |
IEEE Access |
Abbreviated Journal |
ACCESS |
|
| |
Volume |
8 |
Issue |
|
Pages |
17093 - 17102 |
|
| |
Keywords |
|
|
| |
Abstract |
Approaches that use more than two consecutive video frames in the optical flow estimation have a long research history. However, almost all such methods utilize extra information for a pre-processing flow prediction or for a post-processing flow correction and filtering. In contrast, this paper differs from previously developed techniques. We propose a new algorithm for the likelihood function calculation (alternatively the matching cost volume) that is used in the maximum a posteriori estimation. We exploit the fact that in general, optical flow is locally constant in the sense of time and the likelihood function depends on both the previous and the future frame. Implementation of our idea increases the robustness of optical flow estimation. As a result, our method outperforms 9% over the DCFlow technique, which we use as prototype for our CNN based computation architecture, on the most challenging MPI-Sintel dataset for the non-occluded mask metric. Furthermore, our approach considerably increases the accuracy of the flow estimation for the matching cost processing, consequently outperforming the original DCFlow algorithm results up to 50% in occluded regions and up to 9% in non-occluded regions on the MPI-Sintel dataset. The experimental section shows that the proposed method achieves state-of-the-arts results especially on the MPI-Sintel 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; 600.120 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ YCW2020 |
Serial |
3345 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Fei Yang; Luis Herranz; Joost Van de Weijer; Jose Antonio Iglesias; Antonio Lopez; Mikhail Mozerov |
|
| |
Title |
Variable Rate Deep Image Compression with Modulated Autoencoder |
Type |
Journal Article |
| |
Year |
2020 |
Publication |
IEEE Signal Processing Letters |
Abbreviated Journal |
SPL |
|
| |
Volume |
27 |
Issue |
|
Pages |
331-335 |
|
| |
Keywords |
|
|
| |
Abstract |
Variable rate is a requirement for flexible and adaptable image and video compression. However, deep image compression methods (DIC) are optimized for a single fixed rate-distortion (R-D) tradeoff. While this can be addressed by training multiple models for different tradeoffs, the memory requirements increase proportionally to the number of models. Scaling the bottleneck representation of a shared autoencoder can provide variable rate compression with a single shared autoencoder. However, the R-D performance using this simple mechanism degrades in low bitrates, and also shrinks the effective range of bitrates. To address these limitations, we formulate the problem of variable R-D optimization for DIC, and propose modulated autoencoders (MAEs), where the representations of a shared autoencoder are adapted to the specific R-D tradeoff via a modulation network. Jointly training this modulated autoencoder and the modulation network provides an effective way to navigate the R-D operational curve. Our experiments show that the proposed method can achieve almost the same R-D performance of independent models with significantly fewer parameters. |
|
| |
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; ADAS; 600.141; 600.120; 600.118 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ YHW2020 |
Serial |
3346 |
|
| Permanent link to this record |
