Adaptive Soft Contrastive Learning

07/22/2022
by   Chen Feng, et al.
0

Self-supervised learning has recently achieved great success in representation learning without human annotations. The dominant method – that is contrastive learning, is generally based on instance discrimination tasks, i.e., individual samples are treated as independent categories. However, presuming all the samples are different contradicts the natural grouping of similar samples in common visual datasets, e.g., multiple views of the same dog. To bridge the gap, this paper proposes an adaptive method that introduces soft inter-sample relations, namely Adaptive Soft Contrastive Learning (ASCL). More specifically, ASCL transforms the original instance discrimination task into a multi-instance soft discrimination task, and adaptively introduces inter-sample relations. As an effective and concise plug-in module for existing self-supervised learning frameworks, ASCL achieves the best performance on several benchmarks in terms of both performance and efficiency. Code is available at https://github.com/MrChenFeng/ASCL_ICPR2022.

READ FULL TEXT
research
06/21/2023

Inter-Instance Similarity Modeling for Contrastive Learning

The existing contrastive learning methods widely adopt one-hot instance ...
research
03/22/2023

MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset

Deep learning has achieved great success in recent years with the aid of...
research
12/15/2021

Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration

Our work reveals a structured shortcoming of the existing mainstream sel...
research
10/10/2021

Weakly Supervised Contrastive Learning

Unsupervised visual representation learning has gained much attention fr...
research
03/30/2023

Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning

Contrastive learning methods train visual encoders by comparing views fr...
research
05/25/2023

Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation

Unsupervised disentanglement is a long-standing challenge in representat...
research
11/02/2022

Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning

Contrastive self-supervised learning (CSL) based on instance discriminat...

Please sign up or login with your details

Forgot password? Click here to reset