Hyperspectral remote sensing technology is swiftly evolving, prioritizing affordability, enhanced portability, seamless integration, sophisticated intelligence, and immediate processing capabilities. The leading model for classifying hyperspectral images, which relies on convolutional neural networks (CNNs), has proven to be highly effective when run on advanced computing platforms. Nonetheless, the high degree of parameterization inherent in CNN models necessitates considerable computational and storage resources, posing challenges to their deployment in processors with limited capacity like drones and satellites. This paper focuses on advancing lightweight models for hyperspectral image classification and introduces EBCNN, a novel binary convolutional neural network. EBCNN is designed to effectively regulate backpropagation gradients and minimize gradient discrepancies to optimize BNN performance. EBCNN incorporates an adaptive gradient scaling module that utilizes a multi-scale pyramid squeeze attention (PSA) mechanism during the training phase, which can adjust training gradients flexibly and efficiently. Additionally, to address suboptimal training issues, EBCNN employs a dynamic curriculum learning strategy underpinned by a confidence-aware loss function, Superloss, enabling progressive binarization and enhancing its classification effectiveness. Extensive experimental evaluations conducted on five esteemed public datasets confirm the effectiveness of EBCNN. These analyses highlight a significant enhancement in the classification accuracy of hyperspectral images, achieved without incurring additional memory or computational overheads during the inference process.

Hyperspectral image cross-scene classification (HSICC) tasks are confronted with tremendous challenges due to spectral shift phenomena across scenes and the tough work of obtaining labels. Unsupervised domain adaptation has proven its effectiveness in tackling this issue, but it has a fatal limitation of intending to narrow the disparity between source and target domains by utilizing fully labeled source data and unlabeled target data. However, it is costly even to attain labels from source domains in many cases, rendering sufficient labeling as used in prior work impractical. In this work, we investigate an extreme and realistic scenario where unsupervised domain adaptation methods encounter sparsely labeled source data when handling HSICC tasks, namely, few-shot unsupervised domain adaptation. We propose an end-to-end refined bi-directional prototypical contrastive learning (RBPCL) framework for overcoming the HSICC problem with only a few labeled samples in the source domain. RBPCL captures category-level semantic features of hyperspectral data and performs feature alignment through in-domain refined prototypical self-supervised learning and bi-directional cross-domain prototypical contrastive learning, respectively. Furthermore, our framework introduces the class-balanced multicentric dynamic prototype strategy to generate more robust and representative prototypes. To facilitate prototype contrastive learning, we employ a Siamese-style distance metric loss function to aggregate intra-class features while increasing the discrepancy of inter-class features. Finally, extensive experiments and ablation analysis implemented on two public cross-scene data pairs and three pairs of self-collected ultralow-altitude hyperspectral datasets under different illumination conditions verify the effectiveness of our method, which will further enhance the practicality of hyperspectral intelligent sensing technology.

Sparse Matrix–Vector Multiplication (SpMV) is a critical computational kernel in high-performance computing (HPC) and artificial intelligence (AI). However, its irregular memory access patterns lead to frequent cache misses on multi-level cache hierarchies, significantly degrading performance. Scratchpad memory (SPM), a software-managed, low-latency on-chip memory, offers improved data locality and control, making it a promising alternative for irregular workloads. To enhance SpMV performance, we propose a vectorized execution framework targeting SPM-augmented processors. Recognizing the limitations of traditional formats for vectorization, we introduce Sorted-Row-Block ELL (SRB-ELL), a new matrix storage format derived from ELLPACK (ELL). SRB-ELL stores only non-zero elements, partitions the matrix into row blocks, and sorts them by block size to improve load balance and SIMD efficiency. We implement and evaluate SRB-ELL on a custom processor architecture with integrated SPM using the gem5 simulator. Experimental results show that, compared to vectorized CSR-based SpMV, the SRB-ELL design achieves up to 1.48× speedup and an average of 1.19×.