DeepAI AI Chat
Log In Sign Up

Can Semantic Labels Assist Self-Supervised Visual Representation Learning?

by   Longhui Wei, et al.

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to fully-supervised methods, seeming to deliver the message that human labels hardly contribute to learning transferrable visual features. In this paper, we defend the usefulness of semantic labels but point out that fully-supervised and self-supervised methods are pursuing different kinds of features. To alleviate this issue, we present a new algorithm named Supervised Contrastive Adjustment in Neighborhood (SCAN) that maximally prevents the semantic guidance from damaging the appearance feature embedding. In a series of downstream tasks, SCAN achieves superior performance compared to previous fully-supervised and self-supervised methods, and sometimes the gain is significant. More importantly, our study reveals that semantic labels are useful in assisting self-supervised methods, opening a new direction for the community.


page 2

page 4

page 8


Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations

Contrastive learning has achieved great success in self-supervised visua...

Semantic-Aware Generation for Self-Supervised Visual Representation Learning

In this paper, we propose a self-supervised visual representation learni...

Mutual Contrastive Learning for Visual Representation Learning

We present a collaborative learning method called Mutual Contrastive Lea...

Self-Supervised Visual Representations Learning by Contrastive Mask Prediction

Advanced self-supervised visual representation learning methods rely on ...

Interventional Contrastive Learning with Meta Semantic Regularizer

Contrastive learning (CL)-based self-supervised learning models learn vi...

Learning Rewards and Skills to Follow Commands with A Data Efficient Visual-Audio Representation

Based on the recent advancements in representation learning, we propose ...

Automatic Shortcut Removal for Self-Supervised Representation Learning

In self-supervised visual representation learning, a feature extractor i...