ACOC-MT: More Effective Handling of Real-World Noisy Labels in Remote Sensing Semantic Segmentation

Zeqing Wang, Yulong Ding, Yixiang Li, Zhaoming Wu, Xuan Yang, Zhengchao Chen

Abstract: In remote sensing (RS) semantic segmentation, imperfect labels are prevalent due to the complexities of data acquisition and annotation processes. Although recent approaches to noisy label correction in RS segmentation have shown promising results, challenges remain in accuracy and generalizability, given the incomplete consideration of the complex mixing involved. Nearly all methods should address three key challenges to identify and correct noisy labels: when to select labels, which labels to select, and how to handle the selected labels. We propose a novel label correction framework, adaptive confidence-guided object-level label correction with mean teacher (ACOC-MT), which effectively addresses all three of these challenges. The ACOC-MT framework determines when to conduct label correction through the stable early learning detection (SELD) module, selects noisy labels using the consistency threshold mask (CTM) module, and corrects the labels through the object label correction (OLC) module. To validate against real-world noisy labels rather than simulated ones, we constructed three real-world noisy-labeled datasets, CPCTC-N, BBD250-N, and CFD-N, from three different RS scenarios. Extensive experiments on these three datasets demonstrate the efficacy and superior performance of our approach.

External IDs:dblp:journals/tgrs/WangDLWYC25