SA-MixNet: Structure-Aware Mixup and Invariance Learning for Scribble-Supervised Road Extraction in Remote Sensing Images

Jie Feng, Hao Huang, Junpeng Zhang, Weisheng Dong, Dingwen Zhang, Licheng Jiao

Research output: Contribution to journalArticlepeer-review

Abstract

Mainstreamed weakly supervised road extractors rely on highly confident pseudo-labels propagated from scribbles, and their performance often degrades gradually as the image scenes tend to vary. We argue that such degradation is due to the poor model's invariance to scenes with different complexities, whereas existing solutions to this problem are commonly based on crafted priors that cannot be derived from scribbles. To eliminate the reliance on such priors, we propose a novel structure-aware mixup and invariance learning framework (SA-MixNet) for weakly supervised road extraction that improves the model invariance in a data-driven manner. Specifically, we design a structure-aware mixup (SA-Mix) scheme to paste road regions from one image onto another to create an image scene with increased complexity while preserving the road's structural integrity. Then, an invariance regularization is imposed on the predictions of constructed and origin images to minimize their conflicts, which thus forces the model to behave consistently in various scenes. Moreover, a discriminator-based regularization is designed to enhance connectivity while preserving the structure of roads. Combining these designs, our framework demonstrates superior performance on the DeepGlobe, Wuhan, and Massachusetts datasets, outperforming the state-of-the-art techniques by 1.47%, 2.12%, and 4.09%, respectively, in IoU metrics, and showing its potential as a plug-and-play solution. Our source code is available at https://github.com/xdu-jjgs.

Original languageEnglish
Article number5602214
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume63
DOIs
StatePublished - 2025

Keywords

  • Adversarial learning
  • cross-view consistency
  • remote sensing
  • road extraction
  • weakly supervised learning

Fingerprint

Dive into the research topics of 'SA-MixNet: Structure-Aware Mixup and Invariance Learning for Scribble-Supervised Road Extraction in Remote Sensing Images'. Together they form a unique fingerprint.

Cite this