CW-BASS: Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation

TL;DR

CW-BASS introduces a confidence-weighted, boundary-aware framework for semi-supervised semantic segmentation, effectively reducing label noise, confirmation bias, and boundary blur, leading to state-of-the-art results on Pascal VOC 2012 and Cityscapes.

Contribution

It proposes novel confidence-weighted loss, dynamic thresholding, and boundary-aware modules specifically designed for semi-supervised segmentation.

Findings

Achieves 65.9% mIoU on Cityscapes with only 3.3% labeled data.

Outperforms existing methods on Pascal VOC 2012 and Cityscapes datasets.

Effectively reduces label noise and boundary blur in semi-supervised learning.

Abstract

Semi-supervised semantic segmentation (SSSS) aims to improve segmentation performance by utilizing large amounts of unlabeled data with limited labeled samples. Existing methods often suffer from coupling, where over-reliance on initial labeled data leads to suboptimal learning; confirmation bias, where incorrect predictions reinforce themselves repeatedly; and boundary blur caused by limited boundary-awareness and ambiguous edge cues. To address these issues, we propose CW-BASS, a novel framework for SSSS. In order to mitigate the impact of incorrect predictions, we assign confidence weights to pseudo-labels. Additionally, we leverage boundary-delineation techniques, which, despite being extensively explored in weakly-supervised semantic segmentation (WSSS), remain underutilized in SSSS. Specifically, our method: (1) reduces coupling via a confidence-weighted loss that adjusts pseudo-label influence based on their predicted confidence scores, (2) mitigates confirmation bias with a dynamic thresholding mechanism that learns to filter out pseudo-labels based on model performance, (3) tackles boundary blur using a boundary-aware module to refine segmentation near object edges, and (4) reduces label noise through a confidence decay strategy that progressively refines pseudo-labels during training. Extensive experiments on Pascal VOC 2012 and Cityscapes demonstrate that CW-BASS achieves state-of-the-art performance. Notably, CW-BASS achieves a 65.9% mIoU on Cityscapes under a challenging and underexplored 1/30 (3.3%) split (100 images), highlighting its effectiveness in limited-label settings. Our code is available at https://github.com/psychofict/CW-BASS.