Deep collaborative learning with class-rebalancing for semi-supervised change detection in SAR images

Xuan Hou, Yunpeng Bai, Yefan Xie, Huibin Ge, Yi Li (Corresponding Author), Changjing Shang (Corresponding Author), Qiang Shen

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)
20 Downloads (Pure)


Deep learning reveals excellent potential for accomplishing change detection in SAR imagery. Yet, it suffers from the problem of requiring large amounts of labeled samples, whilst labeling SAR imagery for change detection requires experts to label individual images at the pixel level, which is extremely tedious and time-consuming. Also, sample imbalance continues to present a serious challenge for the existing change detection techniques. To tackle these problems, in this study, a Deep Collaborative semi-supervised learning Framework with Class-Rebalancing (DCF-CRe) is proposed for SAR imagery change detection, by exploiting Convolutional Neural Network (CNN) and deep clustering. In particular, a Siamese Difference Fusion Network (SDFNet) is devised to implement change detection while effectively reducing the information loss due to the generation of difference images and highlighting features of the changed regions.In so doing, only a tiny batch of labeled samples is utilized to train SDFNet in order to obtain predicted change map and deep features. In addition, the Approximate Rank-Order Clustering (AROC) algorithm is employed to cluster the deep features, generating pseudo-labels for abundant unlabeled samples. DCF-CRe is then applied to select appropriate pseudo-labels and to add labeled samples to train SDFNet. Experimental results evaluated on six challenging datasets show that this proposed approach can achieve performance superior to state-of-the-art change detection methods for SAR imagery.

Original languageEnglish
Article number110281
Number of pages11
JournalKnowledge-Based Systems
Early online date31 Jan 2023
Publication statusPublished - 15 Mar 2023


  • Change detection
  • Collaborative learning
  • Remote sensing
  • SAR images
  • Semi-supervised learning


Dive into the research topics of 'Deep collaborative learning with class-rebalancing for semi-supervised change detection in SAR images'. Together they form a unique fingerprint.

Cite this