MSPD-net: structural–appearance prototype decoupling for weakly supervised semantic segmentation

Wei Cao

doi:10.1007/s00371-026-04715-4

MSPD-net: structural–appearance prototype decoupling for weakly supervised semantic segmentation

2026-08-28

0

PRE

AI

DOI：10.1007/s00371-026-04715-4

Original

Original request for help

Save

Abstract

En 中文

Weakly supervised semantic segmentation (WSSS) based on image-level labels typically relies on class activation maps (CAMs) to generate pseudo-labels. However, single-layer prototype-based generation methods often result in incomplete CAM activation and inaccurate target localization due to limited feature representation capabilities. Furthermore, the reliance of existing methods on discriminative appearance information makes it difficult to effectively utilize object structural information, further impacting boundary accuracy and the final segmentation performance. To address this problem, this paper proposes a complementary prototype representation framework, employing three modules to collaboratively improve pseudo-label quality. First, the Multi-scale prototype fusion module (MSPF) adaptively integrates multi-level features to construct a more complete and accurate category representation. Second, the structural–appearance prototype decoupling module (SAPD) separates appearance and geometric information in pixel-prototype matching, enhancing texture discrimination and boundary details. Finally, Negative prototype clustering mining (NPCM) improves the discriminative ability of confused categories by generating semantically similar sub-category negative samples. Experiments on the PASCAL VOC 2012 and MS COCO 2014 datasets demonstrate that our method achieves 73.3% mIoU (val) and 73.7% mIoU (test) on PASCAL VOC, and 43.7% mIoU on MS COCO. The code is available at https://github.com/Weiw1819/MSPD-Net .

Keywords:

Weakly supervised semantic segmentation

Class activation map

Prototype learning

Structural–appearance decoupling

Multi-scale feature fusion

Contrastive learning

Boundary-aware segmentation

MSPD-net: structural–appearance prototype decoupling for weakly supervised semantic segmentation

Abstract

Journal

Organization

Cited Papers