Abstract
Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples. This paper proposes a new kind of contrastive learning method, named CLIM, which uses positives from other samples in the dataset. This is achieved by searching local similar samples of the anchor, and selecting samples that are closer to the corresponding cluster center, which we denote as center-wise local image selection. The selected samples are instantiated via an data mixture strategy, which performs as a smoothing regularization. As a result, CLIM encourages both local similarity and global aggregation in a robust way, which we find is beneficial for feature representation. Besides, we introduce multi-resolution augmentation, which enables the representation to be scale invariant. We reach 75.5% top-1 accuracy with linear evaluation over ResNet-50, and 59.3% top-1 accuracy when fine-tuned with only 1% labels.
| Original language | English |
|---|---|
| State | Published - 2021 |
| Externally published | Yes |
| Event | 32nd British Machine Vision Conference, BMVC 2021 - Virtual, Online Duration: 22 Nov 2021 → 25 Nov 2021 |
Conference
| Conference | 32nd British Machine Vision Conference, BMVC 2021 |
|---|---|
| City | Virtual, Online |
| Period | 22/11/21 → 25/11/21 |
Fingerprint
Dive into the research topics of 'Center-wise Local Image Mixture For Contrastive Representation Learning'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver