Journal
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
Volume 14, Issue -, Pages 12415-12428Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2021.3129177
Keywords
Feature extraction; Task analysis; Adaptation models; Hyperspectral imaging; Training; Semantics; Image classification; Adversarial learning; domain adaptation (DA); hyperspectral image (HSI) classification; variational autoencoders (VAEs)
Categories
Funding
- National Natural Science Foundation of China [61971141, 61731021]
Ask authors/readers for more resources
This article proposes a coarse-to-fine joint distribution alignment framework for cross-domain classification of HSIs, utilizing VAE and JDA modules. Experimental results demonstrate the superiority of the proposed method in comparison with several conventional and state-of-the-art methods.
Domain adaptation (DA) aims to enhance the feature transferability of a model across different domains with feature distribution differences, which has been widely explored in many computer vision tasks such as semantic segmentation and object detection, but has not been fully studied in hyperspectral image (HSI) classification task. Compared with the natural image-based DA, HSI-based DA still faces two main challenges: First, due to the strong spectral variability of HSIs, it is difficult to extract discriminative and domain-invariant features from different domains, resulting in the misalignment of cross-domain features; Second, class-wise (or fine-grained) spectral feature inconsistency between domains also inevitably degrades the classification accuracy. To address these issues, in this article, we propose a novel coarse-to-fine joint distribution alignment (JDA) framework for cross-domain classification of HSIs. Specifically, the training samples from source and target domains are first fed into a coupled variational autoencoders (VAE) module, which is composed of two well-designed VAEs equipped with mutual information metric to learn high-level domain-invariant representations in a shared latent space, so that the network can learn a coarse-grained source-target feature consistency. Furthermore, to alleviate the class-wise inter-domain feature inconsistency, a JDA module is constructed to perform a fine-grained cross-domain alignment by matching the joint probability distributions between the source and target domains through adversarial learning. Extensive experiments on both simulated and real hyperspectral datasets demonstrate the superiority of the proposed method in comparison with several conventional and state-of-the-art methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available