TAPM-Net: Trajectory-Aware Perturbation Modeling for Infrared Small Target Detection

2026-01-09

arXiv.org

AI Summary

Infrared small target detection remains highly challenging due to low contrast, minute target size, and interference from complex backgrounds, which often cause existing methods to struggle in distinguishing true targets from structured noise. This work proposes TAPM-Net, the first framework to incorporate a trajectory-aware perturbation modeling mechanism. It constructs a multi-level perturbation energy field, extracts directional features via gradient-guided paths, and leverages the Mamba state space model for dynamic trajectory propagation and semantic fusion. Additionally, a velocity-constrained diffusion strategy is introduced to enhance trajectory consistency. The proposed method achieves state-of-the-art performance on the NUAA-SIRST and IRSTD-1K benchmarks, demonstrating superior anisotropic perception, contextual sensitivity, and computational efficiency.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Infrared small target detection (ISTD) remains a long-standing challenge due to weak signal contrast, limited spatial extent, and cluttered backgrounds. Despite performance improvements from convolutional neural networks (CNNs) and Vision Transformers (ViTs), current models lack a mechanism to trace how small targets trigger directional, layer-wise perturbations in the feature space, which is an essential cue for distinguishing signal from structured noise in infrared scenes. To address this limitation, we propose the Trajectory-Aware Mamba Propagation Network (TAPM-Net), which explicitly models the spatial diffusion behavior of target-induced feature disturbances. TAPM-Net is built upon two novel components: a Perturbation-guided Path Module (PGM) and a Trajectory-Aware State Block (TASB). The PGM constructs perturbation energy fields from multi-level features and extracts gradient-following feature trajectories that reflect the directionality of local responses. The resulting feature trajectories are fed into the TASB, a Mamba-based state-space unit that models dynamic propagation along each trajectory while incorporating velocity-constrained diffusion and semantically aligned feature fusion from word-level and sentence-level embeddings. Unlike existing attention-based methods, TAPM-Net enables anisotropic, context-sensitive state transitions along spatial trajectories while maintaining global coherence at low computational cost. Experiments on NUAA-SIRST and IRSTD-1K demonstrate that TAPM-Net achieves state-of-the-art performance in ISTD.

Problem

• Infrared small target detection
• feature perturbation
• trajectory modeling
• structured noise
• spatial diffusion

Innovation

• trajectory-aware modeling
• perturbation propagation
• Mamba state-space model
• infrared small target detection
• anisotropic feature diffusion