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

TL;DR

SA-MixNet introduces a structure-aware data augmentation and invariance learning approach for weakly supervised road extraction, significantly improving performance across multiple remote sensing datasets without relying on handcrafted priors.

Contribution

The paper proposes a novel structure-aware Mixup and invariance learning framework that enhances model invariance and connectivity in weakly supervised road extraction from remote sensing images.

Findings

Outperforms state-of-the-art methods on three datasets by 1.47%-4.09% in IoU.

Demonstrates improved model invariance to scene complexity.

Shows potential as a plug-and-play solution for weakly supervised segmentation.

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 various. 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 scheme to paste road regions from one image onto another for creating 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 on various scenes. Moreover, a discriminator-based regularization is designed for enhancing the connectivity meanwhile 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%, 4.09% respectively in IoU metrics, and showing its potential of plug-and-play. The code will be made publicly available.