Open access
Sep 2026
Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision
Interestingly, despite using zero manual annotations, MoSA achieves segmentation performance comparable to the fully supervised SAM, revealing that harnessing large-scale unlabeled motion is a feasible and highly scalable alternative to annotation-driven segment-anything pipelines.
Wei-Jian Jian, Xiao-Yue Zhang, Bin Xiao et al.
· Lecture Notes in Computer Sc... · 0 citations