English

A Lightweight Clustering Framework for Unsupervised Semantic Segmentation

Computer Vision and Pattern Recognition 2024-01-01 v2

Abstract

Unsupervised semantic segmentation aims to categorize each pixel in an image into a corresponding class without the use of annotated data. It is a widely researched area as obtaining labeled datasets is expensive. While previous works in the field have demonstrated a gradual improvement in model accuracy, most required neural network training. This made segmentation equally expensive, especially when dealing with large-scale datasets. We thus propose a lightweight clustering framework for unsupervised semantic segmentation. We discovered that attention features of the self-supervised Vision Transformer exhibit strong foreground-background differentiability. Therefore, clustering can be employed to effectively separate foreground and background image patches. In our framework, we first perform multilevel clustering across the Dataset-level, Category-level, and Image-level, and maintain consistency throughout. Then, the binary patch-level pseudo-masks extracted are upsampled, refined and finally labeled. Furthermore, we provide a comprehensive analysis of the self-supervised Vision Transformer features and a detailed comparison between DINO and DINOv2 to justify our claims. Our framework demonstrates great promise in unsupervised semantic segmentation and achieves state-of-the-art results on PASCAL VOC and MS COCO datasets.

Keywords

Cite

@article{arxiv.2311.18628,
  title  = {A Lightweight Clustering Framework for Unsupervised Semantic Segmentation},
  author = {Yau Shing Jonathan Cheung and Xi Chen and Lihe Yang and Hengshuang Zhao},
  journal= {arXiv preprint arXiv:2311.18628},
  year   = {2024}
}
R2 v1 2026-06-28T13:37:06.148Z