DS-HyFA-Net: A Deeply Supervised Hybrid Feature Aggregation Network With Multiencoders for Change Detection in High-Resolution Imagery

• Published in: IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-17
• Main Authors: Ying, Zilu, Xian, Tingfeng, Zhai, Yikui, Jia, Xudong, Zhang, Hongsheng, Pan, Jiahao, Coscia, Pasquale, Genovese, Angelo, Piuri, Vincenzo, Scotti, Fabio
• Format: Article
• Language: English
• Subjects: Change detection (CD); Classification algorithms; common feature learning strategy (CFLS); Data mining; deeply supervised (DS); Faces; Feature extraction; hybrid feature aggregation (HyFA) module; Manuals; multiencoder; Principal component analysis; Remote sensing; Representation learning; Support vector machines; Transformers
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2024.3471075

With the advancement of deep learning (DL) technologies, remarkable progress has been achieved in change detection (CD). Existing DL-based methods primarily focus on the discrepancy in bitemporal images, while overlooking the commonality in bitemporal images. However, one of the reasons hindering the improvement of CD performance is the inadequate utilization of image information. To address the above issue, we propose a Deeply Supervised Hybrid Feature Aggregation Network (DS-HyFA-Net). This network predicts changes by integrating the distinctness and the commonality in bitemporal images. Specifically, the DS-HyFA-Net primarily consists of a set of encoders and a Hybrid Feature Aggregation (HyFA) module. It uses a Siamese encoder (or Encoder I) and a specialized encoder (or Encoder II) to extract distinct and common features (CFs) in bitemporal images, respectively. The HyFA module efficiently aggregates distinct and common features (or hybrid features) and generates a change map using a predictor. In addition, a common feature learning strategy (CFLS) is introduced, based on deeply supervised (DS) techniques, to guide Encoder II in learning CFs. Experimental results on three well-recognized datasets demonstrate the effectiveness of the innovative DS-HyFA-Net, achieving F1-Scores of 93.33% on WHU-CD, 90.98% on LEVIR-CD, and 81.14% on SYSU-CD. Our code is available at https://github.com/yikuizhai/DS-HyFA-Net .