Dual Classification Head Self-training Network for Cross-scene Hyperspectral Image Classification

TL;DR

This paper introduces DHSNet, a novel dual classification head self-training network for cross-scene hyperspectral image classification, effectively aligning features across domains and improving classification accuracy despite domain shifts.

Contribution

It proposes the first dual classification head self-training strategy for cross-scene HSI classification, enhancing domain adaptation and feature alignment.

Findings

DHSNet outperforms state-of-the-art methods on three datasets.

The central feature attention mechanism improves scene-invariant feature learning.

The approach effectively mitigates domain gaps and pseudo-label errors.

Abstract

Due to the difficulty of obtaining labeled data for hyperspectral images (HSIs), cross-scene classification has emerged as a widely adopted approach in the remote sensing community. It involves training a model using labeled data from a source domain (SD) and unlabeled data from a target domain (TD), followed by inferencing on the TD. However, variations in the reflectance spectrum of the same object between the SD and the TD, as well as differences in the feature distribution of the same land cover class, pose significant challenges to the performance of cross-scene classification. To address this issue, we propose a dual classification head self-training network (DHSNet). This method aligns class-wise features across domains, ensuring that the trained classifier can accurately classify TD data of different classes. We introduce a dual classification head self-training strategy for the first time in the cross-scene HSI classification field. The proposed approach mitigates domain gap while preventing the accumulation of incorrect pseudo-labels in the model. Additionally, we incorporate a novel central feature attention mechanism to enhance the model's capacity to learn scene-invariant features across domains. Experimental results on three cross-scene HSI datasets demonstrate that the proposed DHSNET significantly outperforms other state-of-the-art approaches. The code for DHSNet will be available at https://github.com/liurongwhm.