Three-Branch Multiscale Abundance Feature Fusion Network for Hyperspectral Image Change Detection

Hyperspectral image change detection (HCD) plays a vital role in remote sensing observation. Although deep learning-based HCD methods have achieved remarkable progress in recent years, several key challenges remain: 1) Mixed pixels in HSI hinder detection precision, resulting in coarse change results; 2) Existing methods that rely solely on abundance maps or coarse fusion of pixel-level and subpixel-level features fail to achieve effective matching between them in semantic description and information dimension, limiting the extraction of fine-grained spatial and spectral information; 3) Most HCD approaches pay limited attention to multi-class change detection (MCD), lacking mechanisms to emphasize minority classes at the feature level, which leads to unsatisfactory performance under class imbalance. To address these issues, a Three-branch Multi-scale Abundance Feature Fusion Network (TMAFN) is proposed. The main contributions are as follows: 1) Abundance maps extracted with superpixel constraints is introduced to provide subpixel-level spatial feature consistency and explicit class proportion information; 2) A spatial-channel-spatial module (SCSM) is developed to extract fine-grained spatial structures and highly discriminative semantic features, adaptively enhancing spatial and spectral distinctions; 3) We specifically design a multi-head cross attention (MHCA) mechanism combined with a multi-scale residual fusion (MSRF) strategy based on abundance maps to guide the network's focus toward minority categories. Extensive experiments conducted on three benchmark hyperspectral datasets demonstrate that TMAFN consistently outperforms state-of-the-art deep learning models in overall accuracy and class-wise F1 score, effectively enhancing the detection of subtle and imbalanced change categories.