We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Multi-match: mutual information maximization and CutEdge for semi-supervised learning.
- Authors
Wu, Yulin; Chen, Lei; Zhao, Dong; Zhou, Hongchao; Zheng, Qinghe
- Abstract
Deep supervised learning has achieved great successes in tackling complex computer vision tasks. However, it typically requires a large amount of data with labels and is expensive in practical applications. Semi-supervised learning, which leverages the hidden structures learned from unlabeled data, has attracted much attention. In this work, a semi-supervised classification model named Multi-Match is proposed, which includes two augmentation branches and encourages the output of the complex augmentation branch to be close to the predictions of the simple augmentation branch. A mutual information (MI) loss is introduced to maximize MI not only between the input and output representation, but also between the class assignments inside the simple augmentation branch. A novel information dropping method named CutEdge is proposed by removing multiple regions near the input edges to further improve the robustness. The experimental results on CIFAR-10, CIFAR-100 and SVHN with different label sizes demonstrate that the proposed model outperforms the compared semi-supervised learning methods. The gains come from the MI loss, the combination of affine transformation and CutEdge, and the use of multiple branches.
- Subjects
SUPERVISED learning; COMPUTER vision; AFFINE transformations; DEEP learning
- Publication
Multimedia Tools & Applications, 2023, Vol 82, Issue 1, p479
- ISSN
1380-7501
- Publication type
Article
- DOI
10.1007/s11042-022-13126-1