Principal Mask Proposals for Unsupervised Semantic Segmentation

Paper Title:

Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals

Published on:

25 April 2024

Primary Category:

Computer Vision and Pattern Recognition

Paper Authors:

Oliver Hahn,

Nikita Araslanov,

Simone Schaub-Meyer,

Stefan Roth

Bullets

Key Details

•

Presents PriMaPs, a method to derive mask proposals directly from SSL features using PCA

•

Proposals guide stochastic EM to fit class prototypes for segmentation

•

Reaches competitive performance across datasets and backbones

•

Boosts state-of-the-art when applied orthogonally

Explore the topics in this paper

expectation maximization

image decomposition

self-supervised learning

semantic segmentation

unsupervised learning

AI generated summary

Principal Mask Proposals for Unsupervised Semantic Segmentation

This paper presents a method called PriMaPs to decompose images into semantically meaningful masks using principal components of self-supervised image features. These masks serve as proposals to guide an expectation-maximization algorithm, PriMaPs-EM, to realize unsupervised semantic segmentation by fitting class prototypes. Despite simplicity, PriMaPs-EM leads to competitive accuracy across datasets and backbone models. Notably, it boosts results when combined with state-of-the-art methods, suggesting it uses representation properties orthogonal to prior work.