Cosine-Normalized Attention for Hyperspectral Image Classification

• URL: http://arxiv.org/abs/2604.01763v1
• Date: Thu, 02 Apr 2026 08:32:12 GMT
• Title: Cosine-Normalized Attention for Hyperspectral Image Classification
• Abstract summary: Transformer-based methods have improved hyperspectral image classification (HSIC) by modeling long-range spatial-spectral dependencies.<n>This work revisits attention scoring from a geometric perspective and introduces a cosine-normalized attention formulation.<n> Experiments on three benchmark datasets demonstrate that the proposed approach consistently achieves higher performance.
• Score: 7.170991480063844
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based methods have improved hyperspectral image classification (HSIC) by modeling long-range spatial-spectral dependencies; however, their attention mechanisms typically rely on dot-product similarity, which mixes feature magnitude and orientation and may be suboptimal for hyperspectral data. This work revisits attention scoring from a geometric perspective and introduces a cosine-normalized attention formulation that aligns similarity computation with the angular structure of hyperspectral signatures. By projecting query and key embeddings onto a unit hypersphere and applying a squared cosine similarity, the proposed method emphasizes angular relationships while reducing sensitivity to magnitude variations. The formulation is integrated into a spatial-spectral Transformer and evaluated under extremely limited supervision. Experiments on three benchmark datasets demonstrate that the proposed approach consistently achieves higher performance, outperforming several recent Transformer- and Mamba-based models despite using a lightweight backbone. In addition, a controlled analysis of multiple attention score functions shows that cosine-based scoring provides a reliable inductive bias for hyperspectral representation learning.

Related papers

• Intrinsic and Triangulation-Agnostic Attention: A Simple and Powerful Approach for Learning on Meshes [12.48720424281573]
  This work proposes an adaptation of the attention mechanism for triangle meshes.<n>The core observation is that endowing the attention mechanism with critical properties for learning over meshes -- intrinsicality and triangulation-agnosticism -- enables it to attain state-of-the-art results over several learning-based tasks in geometry-processing.
  arXiv  Detail & Related papers  (2026-07-27T18:04:26Z)
• A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning [52.452902154360565]
  We introduce Mean Curvature Boundary Points (MCBP), a novel geometric framework grounded in Geometric Machine Learning.<n>MCBP explicitly models the intrinsic curvature of the data manifold and computes pointwise mean curvature without requiring principled manifold parametrization.<n>Experiments on synthetic and real-world datasets demonstrate that MCBP consistently improves clustering performance.
  arXiv  Detail & Related papers  (2026-05-05T20:19:09Z)
• Relational Epipolar Graphs for Robust Relative Camera Pose Estimation [0.0]
  A key component of Visual Simultaneous localization and Mapping (VSLAM) is estimating relative camera poses using matched keypoints.<n>In this work, we reformulate relative pose estimation as a relational inference problem over epipolar correspondence graphs.<n>Experiments on indoor and outdoor benchmarks show improved robustness to dense noise and large baseline variation compared to classical and learning-guided approaches.
  arXiv  Detail & Related papers  (2026-04-06T09:29:37Z)
• Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification [4.039576422478934]
  Aerial-ground person re-identification (AG-ReID) is fundamentally challenged by extreme viewpoint and distance discrepancies.<n>Existing methods rely on geometry-aware feature learning or appearance-conditioned prompting.<n>We introduce Geometry-Induced Query-Key Transformation (GIQT), a lightweight low-rank module that rectifies the similarity space by conditioning query-key interactions on camera geometry.
  arXiv  Detail & Related papers  (2026-01-29T08:41:42Z)
• Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models [32.476422580370375]
  Cross-domain sequential recommendation aims to align heterogeneous user behavior sequences collected from different domains.<n>Most researchers interpret cross-attention as residual alignment, where the output is generated by removing redundant and preserving non-redundant information.<n>We introduce Orthogonal Alignment, a phenomenon in which cross-attention discovers novel information that is not present in the query input.
  arXiv  Detail & Related papers  (2025-10-10T14:45:39Z)
• DiffFormer: a Differential Spatial-Spectral Transformer for Hyperspectral Image Classification [3.271106943956333]
  Hyperspectral image classification (HSIC) has gained significant attention because of its potential in analyzing high-dimensional data with rich spectral and spatial information.<n>We propose the Differential Spatial-Spectral Transformer (DiffFormer) to address the inherent challenges of HSIC, such as spectral redundancy and spatial discontinuity.<n>Experiments on benchmark hyperspectral datasets demonstrate the superiority of DiffFormer in terms of classification accuracy, computational efficiency, and generalizability.
  arXiv  Detail & Related papers  (2024-12-23T07:21:41Z)
• Transformers Fusion across Disjoint Samples for Hyperspectral Image Classification [2.1223532600703385]
  3D Swin Transformer (3D-ST) excels in capturing intricate spatial relationships within images. SST specializes in modeling long-range dependencies through self-attention mechanisms. This paper introduces an attentional fusion of these two transformers to significantly enhance the classification performance of Hyperspectral Images (HSIs)
  arXiv  Detail & Related papers  (2024-05-02T08:49:01Z)
• Dynamic Kernel-Based Adaptive Spatial Aggregation for Learned Image Compression [63.56922682378755]
  We focus on extending spatial aggregation capability and propose a dynamic kernel-based transform coding. The proposed adaptive aggregation generates kernel offsets to capture valid information in the content-conditioned range to help transform. Experimental results demonstrate that our method achieves superior rate-distortion performance on three benchmarks compared to the state-of-the-art learning-based methods.
  arXiv  Detail & Related papers  (2023-08-17T01:34:51Z)
• ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution [76.7408734079706]
  Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation. We propose ESSAformer, an ESSA attention-embedded Transformer network for single-HSI-SR with an iterative refining structure.
  arXiv  Detail & Related papers  (2023-07-26T07:45:14Z)
• A Nested Matrix-Tensor Model for Noisy Multi-view Clustering [5.132856740094742]
  We propose a nested matrix-tensor model which extends the spiked rank-one tensor model of order three. We show that our theoretical results allow us to anticipate the exact accuracy of the proposed clustering approach. Our analysis unveils unexpected and non-trivial phase transition phenomena depending on the model parameters.
  arXiv  Detail & Related papers  (2023-05-31T16:13:46Z)
• Deep Diversity-Enhanced Feature Representation of Hyperspectral Images [87.47202258194719]
  We rectify 3D convolution by modifying its topology to enhance the rank upper-bound. We also propose a novel diversity-aware regularization (DA-Reg) term that acts on the feature maps to maximize independence among elements. To demonstrate the superiority of the proposed Re$3$-ConvSet and DA-Reg, we apply them to various HS image processing and analysis tasks.
  arXiv  Detail & Related papers  (2023-01-15T16:19:18Z)
• Data-heterogeneity-aware Mixing for Decentralized Learning [63.83913592085953]
  We characterize the dependence of convergence on the relationship between the mixing weights of the graph and the data heterogeneity across nodes. We propose a metric that quantifies the ability of a graph to mix the current gradients. Motivated by our analysis, we propose an approach that periodically and efficiently optimize the metric.
  arXiv  Detail & Related papers  (2022-04-13T15:54:35Z)
• A Model for Multi-View Residual Covariances based on Perspective Deformation [88.21738020902411]
  We derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups. We validate our model with synthetic and real data and integrate it into photometric and feature-based Bundle Adjustment.
  arXiv  Detail & Related papers  (2022-02-01T21:21:56Z)
• Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation [105.33409035876691]
  This paper explores the problem of multi-view spectral clustering (MVSC) based on tensor low-rank modeling. We design a novel structured tensor low-rank norm tailored to MVSC. We show that the proposed method outperforms state-of-the-art methods to a significant extent.
  arXiv  Detail & Related papers  (2020-04-30T11:52:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.