.png){kind=icon}
.png){kind=icon}
Return
Semi-Supervised Semantic Segmentation With Multi-Constraint Consistency Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2025.3586111.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
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 <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</b>ulti-<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b>onstraint <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b>onsistency <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</b>earning (<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MCCL</b>) 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
Journal
IF:
9.7
Papers:
4.5K
Citations:
2.4W