Sapir Gershov

CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers

In this paper we introduce VoteCut an innovative method for unsupervised object discovery that leverages feature representations from multiple self-supervised models. VoteCut employs normalized-cut based graph partitioning clustering and a pixel voting approach. Additionally We present CuVLER (Cut-V…