Litcius/Paper detail

Adaptive Multitype Contrastive Views Generation for Remote Sensing Image Semantic Segmentation

Cheng Shi, Peiwen Han, Minghua Zhao, Li Fang, Qiguang Miao, Chi‐Man Pun

2025IEEE Transactions on Geoscience and Remote Sensing11 citationsDOI

Abstract

Self-supervised contrastive learning is a powerful pre-training framework for learning the invariant features from the different views of remote sensing images, therefore, the performance of contrastive learning heavily depends on the generation of views. Current view generation is primarily accomplished through different transformations, and the types and parameters of the transformations are require hand-crafted. Hence, the diversity and discriminability of generated views cannot be guaranteed. To address this, we propose a multi-type views optimization method to optimize these transformations. We formulate contrastive learning as a min-max optimization problem, and transformation parameters are optimized by maximizing the contrastive loss. The optimized transformations encourage the negative sample pairs to be close and the positive sample pairs to be far apart. Different from the current adversarial view generation methods, our method can optimize both photometric transformations and geometric transformations. For remote sensing images, the geometric transformation is more critical for view generation, while the existing view optimization methods fail to achieve this. We consider the hue, saturation, brightness, contrast, and geometric rotation transformations in contrastive learning, and evaluate the optimized views on the downstream remote sensing images semantic segmentation task. Extensive experiments are carried on the three remote sensing image segmentation datasets, including ISPRS Potsdam dataset, ISPRS Vaihingen dataset, and LoveDA dataset. Results show that the learned views obtain highly advantages compared to the hand-crafted views and other optimized views. The code associated with this paper has been released and can be accessed at https://github.com/AAAA-CS/AMView.

Topics & Concepts

Computer scienceArtificial intelligenceSegmentationTransformation (genetics)Transformation geometryComputer visionHuePattern recognition (psychology)GeneBiochemistryChemistryDomain Adaptation and Few-Shot LearningAdvanced Image and Video Retrieval TechniquesAdvanced Neural Network Applications