A Novel Image Clustering Algorithm Based on Supported Nearest Neighbors

Unsupervised image clustering is a challenging task in computer vision. Recently, various deep clustering algorithms based on contrastive learning have achieved promising performance and some distinguishable features representation were obtained only by taking different augmented views of same image as positive pairs and maximizing their similarities, whereas taking other images' augmentations in the same batch as negative pairs and minimizing their similarities. However, due to the fact that there is more than one image in a batch belong to the same class, simply pushing the negative instances apart will result in inter-class conflictions and lead to the clustering performance degradation. In order to solve this problem, we propose a deep clustering algorithm based on supported nearest neighbors (SNDC), which constructs positive pairs of current images by maintaining a support set and find its k nearest neighbors from the support set. By going beyond single instance positive, SNDC can learn more generalized features representation with inherent semantic meaning and therefore alleviating inter-class conflictions. Experimental results on multiple benchmark datasets show that the performance of SNDC is superior to the state-of-the-art clustering models, with accuracy improvement of 6.2% and 20.5% on CIFAR-10 and ImageNet-Dogs respectively.

Automated summary

Unsupervised image clustering is a challenging task in computer vision. In this paper, a deep clustering algorithm based on supported nearest neighbors (SNDC) is proposed to solve the inter-class conflictions problem in deep clustering models. By constructing positive pairs with a support set, SNDC learns more generalized features representation with inherent semantic meaning, leading to superior performance compared to state-of-the-art clustering models on multiple benchmark datasets. The experimental results show accuracy improvements of 6.2% and 20.5% on CIFAR-10 and ImageNet-Dogs respectively.