Doubly Contrastive Deep Clustering

03/09/2021
by   Zhiyuan Dang, et al.
21

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 <https://github.com/ZhiyuanDang/DCDC>.

READ FULL TEXT

page 1

page 4

page 7

research
11/14/2022

C3: Cross-instance guided Contrastive Clustering

Clustering is the task of gathering similar data samples into clusters w...
research
09/01/2021

Multi-Sample based Contrastive Loss for Top-k Recommendation

The top-k recommendation is a fundamental task in recommendation systems...
research
01/11/2023

Heterogeneous Tri-stream Clustering Network

Contrastive deep clustering has recently gained significant attention wi...
research
07/12/2023

Mini-Batch Optimization of Contrastive Loss

Contrastive learning has gained significant attention as a method for se...
research
07/04/2022

Positive-Negative Equal Contrastive Loss for Semantic Segmentation

The contextual information is critical for various computer vision tasks...
research
10/27/2021

Robust Contrastive Learning Using Negative Samples with Diminished Semantics

Unsupervised learning has recently made exceptional progress because of ...
research
10/16/2022

Towards Effective Image Manipulation Detection with Proposal Contrastive Learning

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

Please sign up or login with your details

Forgot password? Click here to reset