MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset

by   Chen Feng, et al.

Deep learning has achieved great success in recent years with the aid of advanced neural network structures and large-scale human-annotated datasets. However, it is often costly and difficult to accurately and efficiently annotate large-scale datasets, especially for some specialized domains where fine-grained labels are required. In this setting, coarse labels are much easier to acquire as they do not require expert knowledge. In this work, we propose a contrastive learning method, called Masked Contrastive learning (MaskCon) to address the under-explored problem setting, where we learn with a coarse-labelled dataset in order to address a finer labelling problem. More specifically, within the contrastive learning framework, for each sample our method generates soft-labels with the aid of coarse labels against other samples and another augmented view of the sample in question. By contrast to self-supervised contrastive learning where only the sample's augmentations are considered hard positives, and in supervised contrastive learning where only samples with the same coarse labels are considered hard positives, we propose soft labels based on sample distances, that are masked by the coarse labels. This allows us to utilize both inter-sample relations and coarse labels. We demonstrate that our method can obtain as special cases many existing state-of-the-art works and that it provides tighter bounds on the generalization error. Experimentally, our method achieves significant improvement over the current state-of-the-art in various datasets, including CIFAR10, CIFAR100, ImageNet-1K, Standford Online Products and Stanford Cars196 datasets. Code and annotations are available at


page 8

page 13


Adaptive Soft Contrastive Learning

Self-supervised learning has recently achieved great success in represen...

Contrastive Learning with Boosted Memorization

Self-supervised learning has achieved a great success in the representat...

Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning

Contrastive representation learning has proven to be an effective self-s...

Text-Based Person Search with Limited Data

Text-based person search (TBPS) aims at retrieving a target person from ...

SemPPL: Predicting pseudo-labels for better contrastive representations

Learning from large amounts of unsupervised data and a small amount of s...

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Understanding spatial relations (e.g., "laptop on table") in visual inpu...

Brain-Aware Replacements for Supervised Contrastive Learning

We propose a novel framework for Alzheimer's disease (AD) detection usin...

Please sign up or login with your details

Forgot password? Click here to reset