Log In Sign Up

Doubly Contrastive Deep Clustering

by   Zhiyuan Dang, et al.

Deep clustering successfully provides more effective features than conventional ones and thus becomes an important technique in current unsupervised learning. However, most deep clustering methods ignore the vital positive and negative pairs introduced by data augmentation and further the significance of contrastive learning, which leads to suboptimal performance. In this paper, we present a novel Doubly Contrastive Deep Clustering (DCDC) framework, which constructs contrastive loss over both sample and class views to obtain more discriminative features and competitive results. Specifically, for the sample view, we set the class distribution of the original sample and its augmented version as positive sample pairs and set one of the other augmented samples as negative sample pairs. After that, we can adopt the sample-wise contrastive loss to pull positive sample pairs together and push negative sample pairs apart. Similarly, for the class view, we build the positive and negative pairs from the sample distribution of the class. In this way, two contrastive losses successfully constrain the clustering results of mini-batch samples in both sample and class level. Extensive experimental results on six benchmark datasets demonstrate the superiority of our proposed model against state-of-the-art methods. Particularly in the challenging dataset Tiny-ImageNet, our method leads 5.6% against the latest comparison method. Our code will be available at <>.


page 1

page 4

page 7


C3: Cross-instance guided Contrastive Clustering

Clustering is the task of gathering similar data samples into clusters w...

Multi-Sample based Contrastive Loss for Top-k Recommendation

The top-k recommendation is a fundamental task in recommendation systems...

Positive-Negative Equal Contrastive Loss for Semantic Segmentation

The contextual information is critical for various computer vision tasks...

Robust Contrastive Learning Using Negative Samples with Diminished Semantics

Unsupervised learning has recently made exceptional progress because of ...

Towards Effective Image Manipulation Detection with Proposal Contrastive Learning

Deep models have been widely and successfully used in image manipulation...

Exploring Non-Contrastive Representation Learning for Deep Clustering

Existing deep clustering methods rely on contrastive learning for repres...

Neighborhood Contrastive Learning for Novel Class Discovery

In this paper, we address Novel Class Discovery (NCD), the task of unvei...

Code Repositories


This is the official Pytorch implementation of DCDC:

view repo