Skip to yearly menu bar Skip to main content


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

Shahaf Arica · Or Rubin · Sapir Gershov · Shlomi Laufer

Arch 4A-E Poster #347
[ ] [ Project Page ]
Fri 21 Jun 10:30 a.m. PDT — noon PDT


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-Vote-and-LEaRn), a zero-shot model, trained using pseudo-labels, generated by VoteCut, and a novel soft target loss to refine segmentation accuracy. Through rigorous evaluations across multiple datasets and several unsupervised setups, our methods demonstrate significant improvements in comparison to previous state-of-the-art models. Our ablation studies further highlight the contributions of each component, revealing the robustness and efficacy of our approach. Collectively, VoteCut and CuVLER pave the way for future advancements in image segmentation.

Live content is unavailable. Log in and register to view live content