Contrastive Clustering

21 Sep 2020  ·  Yunfan Li, Peng Hu, Zitao Liu, Dezhong Peng, Joey Tianyi Zhou, Xi Peng ·

In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. To be specific, for a given dataset, the positive and negative instance pairs are constructed through data augmentations and then projected into a feature space. Therein, the instance- and cluster-level contrastive learning are respectively conducted in the row and column space by maximizing the similarities of positive pairs while minimizing those of negative ones. Our key observation is that the rows of the feature matrix could be regarded as soft labels of instances, and accordingly the columns could be further regarded as cluster representations. By simultaneously optimizing the instance- and cluster-level contrastive loss, the model jointly learns representations and cluster assignments in an end-to-end manner. Extensive experimental results show that CC remarkably outperforms 17 competitive clustering methods on six challenging image benchmarks. In particular, CC achieves an NMI of 0.705 (0.431) on the CIFAR-10 (CIFAR-100) dataset, which is an up to 19\% (39\%) performance improvement compared with the best baseline.

PDF Abstract

Results from the Paper


Ranked #4 on Image Clustering on STL-10 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Image Clustering CIFAR-10 CC Accuracy 0.79 # 19
NMI 0.705 # 16
Train set Train+Test # 1
ARI 0.637 # 17
Backbone ResNet34 # 1
Image Clustering CIFAR-100 CC Accuracy 0.429 # 14
NMI 0.431 # 12
ARI 0.266 # 13
Image Clustering ImageNet-10 CC Accuracy 0.893 # 9
NMI 0.859 # 9
ARI 0.822 # 9
Image Size 224 # 1
Image Clustering Imagenet-dog-15 CC Accuracy 0.429 # 11
NMI 0.445 # 10
ARI 0.274 # 11
Image Size 224 # 1
Image Clustering STL-10 CC Accuracy 0.85 # 7
NMI 0.764 # 4
Train Split Train+Test # 1
Backbone ResNet34 # 1
Image Clustering Tiny-ImageNet CC Accuracy 0.14 # 5
NMI 0.34 # 4
ARI 0.071 # 4

Methods