HSOD-BIT-V2: A New Challenging Benchmarkfor Hyperspectral Salient Object Detection

2025-03-18

AI Summary

To address the lack of high-quality benchmark datasets and dedicated models for hyperspectral salient object detection (HSOD), this work introduces HSOD-BIT-V2—the largest and most challenging HSOD benchmark to date—systematically defining and incorporating five realistic challenges, including small objects and spectral similarity between foreground and background. We further propose Hyper-HRNet, the first hyperspectral-specific high-resolution multi-scale network, which integrates spectral self-similarity modeling, global-local collaborative attention, and multi-level feature reconstruction to simultaneously preserve spectral fidelity and enhance fine-grained spatial localization. Extensive experiments demonstrate that Hyper-HRNet achieves significant improvements in mF-measure over state-of-the-art methods on HSOD-BIT-V2, with gains exceeding 8.2% for small objects and low-contrast scenes—validating the critical contribution of spectral information to saliency detection.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Salient Object Detection (SOD) is crucial in computer vision, yet RGB-based methods face limitations in challenging scenes, such as small objects and similar color features. Hyperspectral images provide a promising solution for more accurate Hyperspectral Salient Object Detection (HSOD) by abundant spectral information, while HSOD methods are hindered by the lack of extensive and available datasets. In this context, we introduce HSOD-BIT-V2, the largest and most challenging HSOD benchmark dataset to date. Five distinct challenges focusing on small objects and foreground-background similarity are designed to emphasize spectral advantages and real-world complexity. To tackle these challenges, we propose Hyper-HRNet, a high-resolution HSOD network. Hyper-HRNet effectively extracts, integrates, and preserves effective spectral information while reducing dimensionality by capturing the self-similar spectral features. Additionally, it conveys fine details and precisely locates object contours by incorporating comprehensive global information and detailed object saliency representations. Experimental analysis demonstrates that Hyper-HRNet outperforms existing models, especially in challenging scenarios.

Problem

• Addresses limitations of RGB-based Salient Object Detection in complex scenes.
• Introduces HSOD-BIT-V2, the largest hyperspectral salient object detection dataset.
• Proposes Hyper-HRNet for improved spectral information extraction and object detection.

Innovation

• Introduces HSOD-BIT-V2, largest HSOD benchmark dataset
• Proposes Hyper-HRNet for high-resolution spectral detection
• Captures self-similar spectral features, reduces dimensionality