Semantic Segmentation in Aerial Imagery Using Multi-level Contrastive Learning with Local Consistency

• Published in: 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) pp. 3787 - 3796
• Main Authors: Tang, Maofeng, Georgiou, Konstantinos, Qi, Hairong, Champion, Cody, Bosch, Marc
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.01.2023
• Subjects: Algorithms: Image recognition and understanding (object detection; categorization; Computer vision; Decoding; Image analysis; Remote Sensing; Representation learning; segmentation; Semantic segmentation; Semantics; Task analysis
• ISSN: 2642-9381
• DOI: 10.1109/WACV56688.2023.00379

Semantic segmentation in large-scale aerial images is an extremely challenging task. On one hand, the limited ground truth, as compared to the vast area the images cover, greatly hinders the development of supervised representation learning. On the other hand, the large footprint from remote sensing raises new challenges for semantic segmentation. In addition, the complex and ever changing image acquisition conditions further complicate the problem where domain shifting commonly occurs. In this paper, we exploit self-supervised contrastive learning (CL) methodologies for semantic segmentation in aerial imagery. In addition to performing CL at the feature level as most practices do, we add another level of contrastive learning, at the semantic level, taking advantage of the segmentation output from the downstream task. Further, we embed local mutual information in the semantic-level CL to enforce local consistency. This has largely enhanced the representation power at each pixel and improved the generalization capacity of the trained model. We refer to the proposed approach as multi-level contrastive learning with local consistency (mCL-LC). The experimental results on different benchmarks indicate that the proposed mCL-LC exhibits superior performance as compared to other state-of-the-art contrastive learning frameworks for the semantic segmentation task. mCL-LC also carries better generalization capacity especially when domain shifting exists.