Cross-scene hyperspectral image classification aims to identify a new scene in target domain via learned knowledge from source domain using limited training samples. Existing cross-scene alignment approaches focus on aligning the global feature distribution between the source and target domains while overlooking the fine-grained alignment at different levels. Moreover, they mainly use Transformer architectures to model long-range dependencies across different channels but confront efficiency challenges due to their quadratic complexity, which limits classification performance in unsupervised domain adaptation tasks. To address these issues, a new domain-adaptive Mamba (DAMamba) is proposed for cross-scene hyperspectral image classification. First, a spectral-spatial Mamba is developed to extract high-order semantic features from the input data. Then, a domain-invariant prototype alignment method is proposed from three perspectives, i.e., intra-domain, inter-domain, and mini-batch, to produce reliable pseudo-labels and mitigate the spectral shift between the source and target domains. Finally, a fully connected layer is applied to the aligned features in the target domain to obtain the final classification results. Extensive evaluations across diverse cross-scene datasets demonstrate that our DAMamba outperforms existing state-of-the-art methods in classification accuracy and computing time. The code of this paper is available at https://github.com/PuhongDuan/DAMamba.

Deep learning-based methods for hyperspectral image classification (HSIC) have been widely utilized in recent years. However, existing HSIC methods do not adequately account for illumination variations in HSIs, particularly in urban areas where shadows created by complex ground objects result in significant variations that cannot be ignored. Additionally, when dealing with limited labeled data, most deep learning methods are prone to overfitting, resulting in poor classification performance. To address these challenges, we propose a new Retinex-based dual-branch feature extraction network (RDFEN) for HSIC. First, by incorporating Retinex theory, we propose a hyperspectral Retinex (HyperRetinex) module to extract illumination attributes and reflectance attributes. Then, we propose a dual-branch feature extraction network, which consists of two submodules: illumination attributes feature extraction (IAFE) module and reflectance attributes feature extraction (RAFE) module. Finally, an illumination-reflectance attributes interaction attention fusion (IRAIAF) module is strategically designed to integrate distinct features. Experiments on four benchmark HSI datasets demonstrate that the proposed method outperforms other state-of-the-art HSIC methods, achieving up to 96.85% overall accuracy on the Pavia University dataset, thereby highlighting its effectiveness and robustness in HSIC. For reproducibility, the code is available at https://github.com/JT-shen/Code.

Deep learning models have performed well on many NLP tasks. However, their internal mechanisms are typically difficult for humans to understand. The development of methods to explain models has become a key issue in the reliability of deep learning models in many important applications. Various saliency explanation methods, which give each feature of input a score proportional to the contribution of output, have been proposed to determine the part of the input which a model values most. Despite a considerable body of work on the evaluation of saliency methods, whether the results of various evaluation metrics agree with human cognition remains an open question. In this study, we propose a new human-based method to evaluate saliency methods in NLP by crowdsourcing. We recruited 800 crowd workers and empirically evaluated seven saliency methods on two datasets with the proposed method. We analyzed the performance of saliency methods, compared our results with existing automated evaluation methods, and identified notable differences between NLP and computer vision (CV) fields when using saliency methods. The instance-level data of our crowdsourced experiments and the code to reproduce the explanations are available at https://github.com/xtlu/lreccoling_evaluation.

Crowdsourcing has been used to collect data at scale in numerous fields. Triplet similarity comparison is a type of crowdsourcing task, in which crowd workers are asked the question “among three given objects, which two are more similar?”, which is relatively easy for humans to answer. However, the comparison can be sometimes based on multiple views, i.e., different independent attributes such as color and shape. Each view may lead to different results for the same three objects. Although an algorithm was proposed in prior work to produce multiview embeddings, it involves at least two problems: (1) the existing algorithm cannot independently predict multiview embeddings for a new sample, and (2) different people may prefer different views. In this study, we propose an end-to-end inductive deep learning framework to solve the multiview representation learning problem. The results show that our proposed method can obtain multiview embeddings of any object, in which each view corresponds to an independent attribute of the object. We collected two datasets from a crowdsourcing platform to experimentally investigate the performance of our proposed approach compared to conventional baseline methods.

Over the past years, the acquisition of hyper-temporal data (HTD) from geostationary orbit remote sensing satellites (GEORSS) has provided numerous new research opportunities. Many factors influence the in-orbit dynamic modulation transfer function (MTF) of GEORSS, making it difficult to satisfy the requirements for space-borne cameras. The MTF compensation (MTFC) technique can effectively optimize the design of dynamic MTFs for GEORSS. The traditional MTFC methods mainly consider the sensor, atmosphere and relative motion of the satellite platform when improving GEORSS image quality. They will introduce new high frequency noise, resulting in image information loss. In this paper, a mixed sparse higher-order non-convex total variation (MS-HONCTV) model-aided MTFC method is proposed. By introducing the group sparse regularization (GSR) term into the MS-HONCTV model, it increases the robustness to noise and hence reduces the degeneration of the MTF produced by satellite’ low pointing stability. The MS-HONCTV model is then applied to solve the problem of image degradation. The quality of remote sensing data is improved by the proposed MTFC and this is achieved without modifying the aperture diameter, focal length, or detector size of the satellite’s optical system. Experimental results show that the proposed MS-HONCTV effectively improves the images’ MTF, SNR, gray mean gradient (GMG) and standard deviation (SD), as evidenced by subjective qualitative analysis and objective quantitative assessments of simulated data, laboratory data, and GF-4 satellite data. Compared with other methods, the SNR of the proposed method is increased by 30%, GMG by 14.21% and SD by 6.3% on average.