Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals
This work addresses the problem of automatically partitioning images into semantic regions without annotations for computer vision researchers, offering an incremental improvement by boosting existing state-of-the-art pipelines.
The paper tackles unsupervised semantic segmentation by proposing PriMaPs (Principal Mask Proposals) to decompose images into semantically meaningful masks using pre-trained models, and achieves competitive results across datasets like Cityscapes and COCO-Stuff with a stochastic expectation-maximization algorithm.
Unsupervised semantic segmentation aims to automatically partition images into semantically meaningful regions by identifying global semantic 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 semantic segmentation by fitting class prototypes to PriMaPs with a stochastic expectation-maximization algorithm, PriMaPs-EM. Despite its conceptual simplicity, PriMaPs-EM leads to competitive results across various pre-trained backbone models, including DINO and DINOv2, and across different datasets, such as Cityscapes, COCO-Stuff, and Potsdam-3. Importantly, PriMaPs-EM is able to boost results when applied orthogonally to current state-of-the-art unsupervised semantic segmentation pipelines. Code is available at https://github.com/visinf/primaps.