Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals

arXiv:2404.16818v1 Announce Type: new
Abstract: Unsupervised semantic segmentation aims to automatically partition images into semantically meaningful regions by identifying global categories within an image corpus without any form of annotation. Building upon recent advances in self-supervised representation learning, we focus on how to leverage these large pre-trained models for the downstream task of unsupervised segmentation. We present PriMaPs - Principal Mask Proposals - decomposing images into semantically meaningful masks based on their feature representation. This allows us to realize unsupervised …

abstract advances annotation arxiv boosting building cs.cv focus form global image images pre-trained models proposals representation representation learning segmentation semantic type unsupervised