Rethinking Alignment and Uniformity in Unsupervised Image Semantic Segmentation
DOI:
https://doi.org/10.1609/aaai.v37i9.26325Keywords:
ML: Unsupervised & Self-Supervised Learning, CV: SegmentationAbstract
Unsupervised image segmentation aims to match low-level visual features with semantic-level representations without outer supervision. In this paper, we address the critical properties from the view of feature alignments and feature uniformity for UISS models. We also make a comparison between UISS and image-wise representation learning. Based on the analysis, we argue that the existing MI-based methods in UISS suffer from representation collapse. By this, we proposed a robust network called Semantic Attention Network(SAN), in which a new module Semantic Attention(SEAT) is proposed to generate pixel-wise and semantic features dynamically. Experimental results on multiple semantic segmentation benchmarks show that our unsupervised segmentation framework specializes in catching semantic representations, which outperforms all the unpretrained and even several pretrained methods.Downloads
Published
2023-06-26
How to Cite
Zhang, D., Li, C., Li, H., Huang, W., Huang, L., & Zhang, J. (2023). Rethinking Alignment and Uniformity in Unsupervised Image Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(9), 11192-11200. https://doi.org/10.1609/aaai.v37i9.26325
Issue
Section
AAAI Technical Track on Machine Learning IV