Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929546331160576 |
|---|---|
| author | Zhang, Yong Zhu, Rui Zhang, Shifeng Zhou, Xu Chen, Shifeng Chen, Xiaofan |
| author_facet | Zhang, Yong Zhu, Rui Zhang, Shifeng Zhou, Xu Chen, Shifeng Chen, Xiaofan |
| contents | Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on improving the diversity of training data, to improve the generalization and robustness of the pre-trained models. To this end, we propose a unified framework to conduct data augmentation in the feature space, known as feature augmentation. This strategy is domain-agnostic, which augments similar features to the original ones and thus improves the data diversity. We perform a systematic investigation of various feature augmentation architectures, the gradient-flow skill, and the relationship between feature augmentation and traditional data augmentation. Our study reveals some practical principles for feature augmentation in self-contrastive learning. By integrating feature augmentation on the instance discrimination or the instance similarity paradigm, we consistently improve the performance of pre-trained feature learning and gain better generalization over the downstream image classification and object detection task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_12396 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look Zhang, Yong Zhu, Rui Zhang, Shifeng Zhou, Xu Chen, Shifeng Chen, Xiaofan Computer Vision and Pattern Recognition Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on improving the diversity of training data, to improve the generalization and robustness of the pre-trained models. To this end, we propose a unified framework to conduct data augmentation in the feature space, known as feature augmentation. This strategy is domain-agnostic, which augments similar features to the original ones and thus improves the data diversity. We perform a systematic investigation of various feature augmentation architectures, the gradient-flow skill, and the relationship between feature augmentation and traditional data augmentation. Our study reveals some practical principles for feature augmentation in self-contrastive learning. By integrating feature augmentation on the instance discrimination or the instance similarity paradigm, we consistently improve the performance of pre-trained feature learning and gain better generalization over the downstream image classification and object detection task. |
| title | Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.12396 |