Semi-Supervised Semantic Segmentation With Multi-Constraint Consistency Learning

Jianjian Yin

doi:10.1109/TMM.2025.3586111

Semi-Supervised Semantic Segmentation With Multi-Constraint Consistency Learning

2025-01-01

0

PRE

AI

Liqiang Nie (Liqiang Nie)

华先胜 (Xian‐Sheng Hua)

DOI：10.1109/TMM.2025.3586111

Original

Original request for help

Save

Abstract

En 中文

Consistency regularization has prevailed in semi-supervised semantic segmentation and achieved promising performance. However, existing methods typically concentrate on enhancing the Image-augmentation based Prediction consistency and optimizing the segmentation network as a whole, resulting in insufficient utilization of potential supervisory information. In this paper, we propose a Multi-Constraint Consistency Learning (MCCL) approach to facilitate the staged enhancement of the encoder and decoder. Specifically, we first design a feature knowledge alignment (FKA) strategy to promote the feature consistency learning of the encoder from image-augmentation. Our FKA encourages the encoder to derive consistent features for strongly and weakly augmented views from the perspectives of point-to-point alignment and prototype-based intra-class compactness. Moreover, we propose a self-adaptive intervention (SAI) module to increase the discrepancy of aligned intermediate feature representations, promoting Feature-perturbation based Prediction consistency learning. Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder. Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance.

Keywords:

Semi-supervised semantic segmentation

consistency regularization

multi-constraint consistency learning

feature knowledge alignment

self-adaptive intervention

Semi-Supervised Semantic Segmentation With Multi-Constraint Consistency Learning

Abstract

Journal

Organization

Cited Papers