Unsupervised Single-Scene Semantic Segmentation for Earth Observation
Open Access
- 12 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-11
Abstract
Earth observation data have huge potential to enrich our knowledge about our planet. An important step in many Earth observation tasks is semantic segmentation. Generally, a large number of pixelwise labeled images are required to train deep models for supervised semantic segmentation. On the contrary, strong intersensor and geographic variations impede the availability of annotated training data in Earth observation. In practice, most Earth observation tasks use only the target scene without assuming availability of any additional scene, labeled or unlabeled. Keeping in mind such constraints, we propose a semantic segmentation method that learns to segment from a single scene, without using any annotation. Earth observation scenes are generally larger than those encountered in typical computer vision datasets. Exploiting this, the proposed method samples smaller unlabeled patches from the scene. For each patch, an alternate view is generated by simple transformations, e.g., addition of noise. Both views are then processed through a two-stream network and weights are iteratively refined using deep clustering, spatial consistency, and contrastive learning in the pixel space. The proposed model automatically segregates the major classes present in the scene and produces the segmentation map. Extensive experiments on four Earth observation datasets collected by different sensors show the effectiveness of the proposed method. Implementation is available at https://gitlab.lrz.de/ai4eo/cd/-/tree/main/unsupContrastiveSemanticSeg .Keywords
Funding Information
- Bundesministerium fr Bildung und Forschung (01DD20001)
- Helmholtz Association (W2-W3-100, ZT-I-PF-5-01)
- Bundesministerium fr Wirtschaft und Energie (50EE2201C)
This publication has 58 references indexed in Scilit:
- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles2016
- Unsupervised Visual Representation Learning by Context Prediction2015
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Semantic segmentation of urban scenes by learning local class interactions2015
- Fully convolutional networks for semantic segmentation2015
- Results of the ISPRS benchmark on urban object detection and 3D building reconstructionISPRS Journal of Photogrammetry and Remote Sensing, 2014
- A Kernel Clustering Algorithm With Fuzzy Factor: Application to SAR Image SegmentationIEEE Geoscience and Remote Sensing Letters, 2013
- THE ISPRS BENCHMARK ON URBAN OBJECT CLASSIFICATION AND 3D BUILDING RECONSTRUCTIONISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012
- Adaptive deconvolutional networks for mid and high level feature learning2011