HyperCOD: The First Challenging Benchmark and Baseline for Hyperspectral Camouflaged Object Detection

2026-01-07

arXiv.org

AI Summary

Existing RGB-based methods struggle to effectively detect camouflaged objects in real-world scenarios due to ambiguities in color and texture, while hyperspectral camouflaged object detection lacks a dedicated large-scale benchmark. To address these limitations, this work introduces HyperCOD, the first challenging benchmark for hyperspectral camouflaged object detection, and proposes HSC-SAM, a novel model that extends the Segment Anything Model (SAM) into the hyperspectral domain. HSC-SAM decouples hyperspectral images into spatial and spectral saliency maps and incorporates a spectral-spatial adaptive prompting mechanism. The model achieves state-of-the-art performance on HyperCOD and demonstrates strong generalization across multiple public hyperspectral datasets, establishing a foundational framework for future research in this emerging field.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Data transparency and provenance

Abstract

RGB-based camouflaged object detection struggles in real-world scenarios where color and texture cues are ambiguous. While hyperspectral image offers a powerful alternative by capturing fine-grained spectral signatures, progress in hyperspectral camouflaged object detection (HCOD) has been critically hampered by the absence of a dedicated, large-scale benchmark. To spur innovation, we introduce HyperCOD, the first challenging benchmark for HCOD. Comprising 350 high-resolution hyperspectral images, It features complex real-world scenarios with minimal objects, intricate shapes, severe occlusions, and dynamic lighting to challenge current models. The advent of foundation models like the Segment Anything Model (SAM) presents a compelling opportunity. To adapt the Segment Anything Model (SAM) for HCOD, we propose HyperSpectral Camouflage-aware SAM (HSC-SAM). HSC-SAM ingeniously reformulates the hyperspectral image by decoupling it into a spatial map fed to SAM's image encoder and a spectral saliency map that serves as an adaptive prompt. This translation effectively bridges the modality gap. Extensive experiments show that HSC-SAM sets a new state-of-the-art on HyperCOD and generalizes robustly to other public HSI datasets. The HyperCOD dataset and our HSC-SAM baseline provide a robust foundation to foster future research in this emerging area.

Problem

• hyperspectral camouflaged object detection
• benchmark
• RGB-based camouflaged object detection
• spectral signatures
• real-world scenarios

Innovation

• Hyperspectral Camouflaged Object Detection
• Benchmark Dataset
• Segment Anything Model
• Spectral-Spatial Decoupling
• Adaptive Prompting