SAMamba: Adaptive State Space Modeling with Hierarchical Vision for Infrared Small Target Detection

TL;DR

SAMamba is a new hierarchical vision framework that improves infrared small target detection by effectively bridging domain gaps, preserving details, and modeling global context efficiently, outperforming existing methods on multiple datasets.

Contribution

It introduces a novel adaptive framework combining feature selection, state-space modeling, and multi-scale feature fusion for enhanced infrared small target detection.

Findings

Outperforms state-of-the-art methods on multiple datasets

Effectively handles heterogeneous backgrounds and varying target scales

Maintains fine-grained details while modeling global context

Abstract

Infrared small target detection (ISTD) is vital for long-range surveillance in military, maritime, and early warning applications. ISTD is challenged by targets occupying less than 0.15% of the image and low distinguishability from complex backgrounds. Existing deep learning methods often suffer from information loss during downsampling and inefficient global context modeling. This paper presents SAMamba, a novel framework integrating SAM2's hierarchical feature learning with Mamba's selective sequence modeling. Key innovations include: (1) A Feature Selection Adapter (FS-Adapter) for efficient natural-to-infrared domain adaptation via dual-stage selection (token-level with a learnable task embedding and channel-wise adaptive transformations); (2) A Cross-Channel State-Space Interaction (CSI) module for efficient global context modeling with linear complexity using selective state space modeling; and (3) A Detail-Preserving Contextual Fusion (DPCF) module that adaptively combines multi-scale features with a gating mechanism to balance high-resolution and low-resolution feature contributions. SAMamba addresses core ISTD challenges by bridging the domain gap, maintaining fine-grained details, and efficiently modeling long-range dependencies. Experiments on NUAA-SIRST, IRSTD-1k, and NUDT-SIRST datasets show SAMamba significantly outperforms state-of-the-art methods, especially in challenging scenarios with heterogeneous backgrounds and varying target scales. Code: https://github.com/zhengshuchen/SAMamba.