Search papers, labs, and topics across Lattice.
This paper introduces Exclusivity-Guided Mask Learning (XMask) for semi-supervised crowd instance segmentation, using an Exclusion-Constrained Dual-Prompt SAM (EDP-SAM) with a Nearest Neighbor Exclusion Circle (NNEC) constraint to generate mask supervision. XMask enforces spatial separation through a discriminative mask objective, incorporating Gaussian smoothing and differentiable center sampling for improved feature continuity and training stability. Experiments on ShanghaiTech A, UCF-QNRF, and JHU++ datasets demonstrate state-of-the-art semi-supervised segmentation and counting performance, unifying counting and instance segmentation.
Achieve state-of-the-art semi-supervised crowd instance segmentation and counting by generating high-quality mask supervision from sparse annotations, effectively bridging the gap between these two tasks.
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. In this paper, we first propose an Exclusion-Constrained Dual-Prompt SAM (EDP-SAM), based on our Nearest Neighbor Exclusion Circle (NNEC) constraint, to generate mask supervision for current datasets. With the aim of segmenting individuals in dense scenes, we then propose Exclusivity-Guided Mask Learning (XMask), which enforces spatial separation through a discriminative mask objective. Gaussian smoothing and a differentiable center sampling strategy are utilized to improve feature continuity and training stability. Building on XMask, we present a semi-supervised crowd counting framework that uses instance mask priors as pseudo-labels, which contain richer shape information than traditional point cues. Extensive experiments on the ShanghaiTech A, UCF-QNRF, and JHU++ datasets (using 5%, 10%, and 40% labeled data) verify that our end-to-end model achieves state-of-the-art semi-supervised segmentation and counting performance, effectively bridging the gap between counting and instance segmentation within a unified framework.
