Bayesian Self-Supervised Contrastive Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916110572453888 |
|---|---|
| author | Liu, Bin Wang, Bang Li, Tianrui |
| author_facet | Liu, Bin Wang, Bang Li, Tianrui |
| contents | Recent years have witnessed many successful applications of contrastive learning in diverse domains, yet its self-supervised version still remains many exciting challenges. As the negative samples are drawn from unlabeled datasets, a randomly selected sample may be actually a false negative to an anchor, leading to incorrect encoder training. This paper proposes a new self-supervised contrastive loss called the BCL loss that still uses random samples from the unlabeled data while correcting the resulting bias with importance weights. The key idea is to design the desired sampling distribution for sampling hard true negative samples under the Bayesian framework. The prominent advantage lies in that the desired sampling distribution is a parametric structure, with a location parameter for debiasing false negative and concentration parameter for mining hard negative, respectively. Experiments validate the effectiveness and superiority of the BCL loss. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_11673 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Bayesian Self-Supervised Contrastive Learning Liu, Bin Wang, Bang Li, Tianrui Machine Learning Recent years have witnessed many successful applications of contrastive learning in diverse domains, yet its self-supervised version still remains many exciting challenges. As the negative samples are drawn from unlabeled datasets, a randomly selected sample may be actually a false negative to an anchor, leading to incorrect encoder training. This paper proposes a new self-supervised contrastive loss called the BCL loss that still uses random samples from the unlabeled data while correcting the resulting bias with importance weights. The key idea is to design the desired sampling distribution for sampling hard true negative samples under the Bayesian framework. The prominent advantage lies in that the desired sampling distribution is a parametric structure, with a location parameter for debiasing false negative and concentration parameter for mining hard negative, respectively. Experiments validate the effectiveness and superiority of the BCL loss. |
| title | Bayesian Self-Supervised Contrastive Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2301.11673 |