Contextrast++: Robust Multi-Scale Contextual Contrastive Learning for Semantic Segmentation

2026-08-23

AI Summary

针对语义分割中上下文捕捉及长尾分布问题，提出Contextrast++方法，通过多尺度特征融合与边界感知负采样提升性能。

Abstract

Semantic segmentation has rapidly advanced with deep learning; however, challenges remain in effectively capturing local and global contexts as well as addressing the long-tailed distribution problem. To tackle these issues, we present Contextrast++, a robust contrastive learning method for semantic segmentation that improves multi-scale feature integration and mitigates class imbalance issues. Our method consists of two key components: 1) contextual contrastive learning (CCL) and 2) boundary-aware negative (BANE) sampling. CCL includes three subcomponents: adaptive fusion module, pixel-to-anchor (PA) loss, and anchor-to-anchor (AA) loss. The adaptive fusion module dynamically balances local and global feature integration, resulting in a more context-aware representation. While the PA loss leverages the fused multi-scale features to improve feature representation learning, the AA loss focuses on addressing the long-tailed distribution problem by utilizing a memory bank that stores a fixed number of class-balanced representative anchors. Meanwhile, BANE sampling enhances segmentation precision by selecting hard negatives from misclassified boundary regions, which refines fine-grained details during contrastive learning. As verified in extensive experiments using public datasets, we demonstrate that Contextrast++ substantially improves semantic segmentation performance over existing contrastive learning-based state-of-the-art approaches, while introducing no additional computational overhead during inference.

Problem

• semantic segmentation
• contextual learning
• long-tailed distribution

Innovation

• contextual contrastive learning
• boundary-aware negative sampling
• adaptive fusion module
• long-tailed distribution