Toward Stable Semi-Supervised Remote Sensing Segmentation via Co-Guidance and Co-Fusion

TL;DR

This paper introduces Co2S, a stable semi-supervised remote sensing segmentation framework that combines vision-language and self-supervised models with semantic co-guidance and feature fusion to improve accuracy and reduce pseudo-label drift.

Contribution

The work proposes a novel dual-student architecture with explicit-implicit semantic guidance and global-local feature fusion, addressing pseudo-label drift in semi-supervised remote sensing segmentation.

Findings

Achieves state-of-the-art performance on six datasets.

Effectively mitigates pseudo-label drift and confirmation bias.

Demonstrates robustness across various scenarios.

Abstract

Semi-supervised remote sensing (RS) image semantic segmentation offers a promising solution to alleviate the burden of exhaustive annotation, yet it fundamentally struggles with pseudo-label drift, a phenomenon where confirmation bias leads to the accumulation of errors during training. In this work, we propose Co2S, a stable semi-supervised RS segmentation framework that synergistically fuses priors from vision-language models and self-supervised models. Specifically, we construct a heterogeneous dual-student architecture comprising two distinct ViT-based vision foundation models initialized with pretrained CLIP and DINOv3 to mitigate error accumulation and pseudo-label drift. To effectively incorporate these distinct priors, an explicit-implicit semantic co-guidance mechanism is introduced that utilizes text embeddings and learnable queries to provide explicit and implicit class-level guidance, respectively, thereby jointly enhancing semantic consistency. Furthermore, a global-local feature collaborative fusion strategy is developed to effectively fuse the global contextual information captured by CLIP with the local details produced by DINOv3, enabling the model to generate highly precise segmentation results. Extensive experiments on six popular datasets demonstrate the superiority of the proposed method, which consistently achieves leading performance across various partition protocols and diverse scenarios. Project page is available at https://xavierjiezou.github.io/Co2S/.