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

TL;DR

This paper introduces a novel semi-supervised crowd analysis framework that leverages exclusivity-guided mask learning and a new mask supervision method to improve instance segmentation and counting in dense scenes with limited labels.

Contribution

The paper proposes Exclusion-Constrained Dual-Prompt SAM and XMask, novel methods for mask supervision and spatial separation, advancing semi-supervised crowd segmentation and counting.

Findings

Achieves state-of-the-art semi-supervised segmentation performance.

Effectively uses limited labeled data (5-40%) across multiple datasets.

Bridges the gap between counting and instance segmentation.

Abstract

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.