HCLNet
under review in International Society for Photogrammetry and Remote Sensing, 2023
Recommended citation: Cai Jianfeng. (2024). "Contrastive Learning-Based Heterogeneous Network for PolSAR Land Cover Classification." arXiv preprint arXiv: 2403.19902, 2024. https://arxiv.org/abs/2403.19902
This paper proposes a Heterogeneous Network based on Contrastive Learning (HCLNet). HCLNet aims to learn high-level representation from unlabeled PolSAR data for few-shot classification according to multi-features. It introduces the heterogeneous network for the first time to utilize different PolSAR features better. Beyond the conventional CL, HCLNet develops two easy-to-use plugins to narrow the domain gap between optics and PolSAR, including beam search and superpixel-based instance discrimination. The pre-trained online network is used for the downstream task by fine-tuning. Experiments demonstrate the superiority of HCLNet on three widely used PolSAR benchmark data sets compared with state-of-the-art methods on few-shot classification. Ablation studies also verify the importance of each component. Besides, this work has implications for how to efficiently utilize the multifeatures of PolSAR data to learn better high-level representation in CL and how to construct networks suitable for PolSAR data better.
Recommended citation: Cai Jianfeng. (2024). "Contrastive Learning-Based Heterogeneous Network for PolSAR Land Cover Classification." arXiv preprint arXiv: 2403.19902, 2024.