Vision-Language-Guided Pseudo-Labels for Unsupervised Domain Adaptation in Semantic Segmentation for Waste Sorting

2026-09-01

AI Summary

针对废物分类中语义分割标记数据获取困难的问题，提出一种基于视觉-语言引导的伪标签方法，利用SAM和EVA-CLIP生成高质量伪标签以实现无监督领域自适应。

Abstract

Obtaining labeled data for semantic segmentation in applied settings (e.g., autonomous driving, industrial waste sorting) is expensive and often infeasible at scale. We present a cross-modal pseudo-labeling pipeline that enables unsupervised domain adaptation without any target-domain annotations. The pipeline is built on two core foundation models: SAM generates class-agnostic region proposals, and EVA-CLIP assigns semantic labels based on region-text similarity, with confidence filtering ensuring that only reliable pseudo-labels are used for self-training a segmentation model. As an optional extension, BLIP provides language-grounded verification for ambiguous regions, thereby improving pseudo-label quality without altering the overall pipeline. Evaluated on two domain shifts, synthetic-to-real autonomous driving and, with a primary focus, lab-to-factory industrial waste sorting, the pipeline consistently improves over source-only baselines. Our results demonstrate that pseudo-label quality, not quantity, is a decisive factor in self-training under domain shift, and that cross-modal language grounding offers a practical path to reliable automatic annotation in deployment-critical applications.

Problem

• Unsupervised Domain Adaptation
• Semantic Segmentation
• Pseudo-Labels
• Waste Sorting
• Cross-modal

Innovation

• cross-modal pseudo-labeling
• unsupervised domain adaptation
• language grounding
• self-training
• semantic segmentation