Keywords: Transfer Learning, Unsupervised Learning, Self-supervised Learning
Abstract: Contrastive visual pretraining based on the instance discrimination pretext task has made significant progress. Notably, recent work on unsupervised pretraining has shown to surpass the supervised counterpart for finetuning downstream applications such as object detection and segmentation. It comes as a surprise that image annotations would be better left unused for transfer learning. In this work, we investigate the following problems: What makes instance discrimination pretraining good for transfer learning? What knowledge is actually learned and transferred from these models? From this understanding of instance discrimination, how can we better exploit human annotation labels for pretraining? Our findings are threefold. First, what truly matters for the transfer is low-level and mid-level representations, not high-level representations. Second, the intra-category invariance enforced by the traditional supervised model weakens transferability by increasing task misalignment. Finally, supervised pretraining can be strengthened by following an exemplar-based approach without explicit constraints among the instances within the same category.
One-sentence Summary: Understanding why self-supervised contrastive learning outperforms supervised counterparts for image pretraining
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Data: [ImageNet](https://paperswithcode.com/dataset/imagenet), [MAFL](https://paperswithcode.com/dataset/mafl), [SYNTHIA](https://paperswithcode.com/dataset/synthia), [mini-Imagenet](https://paperswithcode.com/dataset/mini-imagenet)