AI RESEARCH

Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting

arXiv CS.CV

ArXi:2603.16241v1 Announce Type: new Semi-supervised crowd analysis is a prominent area of research, as unlabeled data are typically abundant and inexpensive to obtain. However, traditional point-based annotations constrain performance because individual regions are inherently ambiguous, and consequently, learning fine-grained structural semantics from sparse anno tations remains an unresolved challenge.