Log In Sign Up

Revisiting Contrastive Learning for Few-Shot Classification

by   Orchid Majumder, et al.

Instance discrimination based contrastive learning has emerged as a leading approach for self-supervised learning of visual representations. Yet, its generalization to novel tasks remains elusive when compared to representations learned with supervision, especially in the few-shot setting. We demonstrate how one can incorporate supervision in the instance discrimination based contrastive self-supervised learning framework to learn representations that generalize better to novel tasks. We call our approach CIDS (Contrastive Instance Discrimination with Supervision). CIDS performs favorably compared to existing algorithms on popular few-shot benchmarks like Mini-ImageNet or Tiered-ImageNet. We also propose a novel model selection algorithm that can be used in conjunction with a universal embedding trained using CIDS to outperform state-of-the-art algorithms on the challenging Meta-Dataset benchmark.


A Simple Framework for Contrastive Learning of Visual Representations

This paper presents SimCLR: a simple framework for contrastive learning ...

Understanding the properties and limitations of contrastive learning for Out-of-Distribution detection

A recent popular approach to out-of-distribution (OOD) detection is base...

K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations

In this paper, we propose the K-Shot Contrastive Learning (KSCL) of visu...

Are all negatives created equal in contrastive instance discrimination?

Self-supervised learning has recently begun to rival supervised learning...

GANORCON: Are Generative Models Useful for Few-shot Segmentation?

Advances in generative modeling based on GANs has motivated the communit...

Using Navigational Information to Learn Visual Representations

Children learn to build a visual representation of the world from unsupe...

Self-Supervised Visual Representations Learning by Contrastive Mask Prediction

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