MLCRNet: Multi-Level Context Refinement for Semantic Segmentation in Aerial Images

• Published in: Remote sensing (Basel, Switzerland) Vol. 14; no. 6; p. 1498
• Main Authors: Huang, Zhifeng, Zhang, Qian, Zhang, Guixu
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-03-2022
• Subjects: aerial imagery; Agglomeration; Aggregates; Context; Deep learning; feature extraction; feature refinement; Image processing; Image segmentation; Modules; multi-level context modeling; Neural networks; Redundancy; Remote sensing; Representations; Semantic segmentation; Semantics; Teaching methods
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs14061498

In this paper, we focus on the problem of contextual aggregation in the semantic segmentation of aerial images. Current contextual aggregation methods only aggregate contextual information within specific regions to improve feature representation, which may yield poorly robust contextual information. To address this problem, we propose a novel multi-level context refinement network (MLCRNet) that aggregates three levels of contextual information effectively and efficiently in an adaptive manner. First, we designed a local-level context aggregation module to capture local information around each pixel. Second, we integrate multiple levels of context, namely, local-level, image-level, and semantic-level, to aggregate contextual information from a comprehensive perspective dynamically. Third, we propose an efficient multi-level context transform (EMCT) module to address feature redundancy and to improve the efficiency of our multi-level contexts. Finally, based on the EMCT module and feature pyramid network (FPN) framework, we propose a multi-level context feature refinement (MLCR) module to enhance feature representation by leveraging multi-level contextual information. Extensive empirical evidence demonstrates that our MLCRNet achieves state-of-the-art performance on the ISPRS Potsdam and Vaihingen datasets.