FeedbackSTS-Det: Sparse Frames-Based Spatio-Temporal Semantic Feedback Network for Infrared Small Target Detection

2026-01-21

AI Summary

This work addresses the challenges of infrared small target detection under complex backgrounds, where low signal-to-clutter ratios, strong dynamic interference, and weak target signatures hinder existing methods from effectively modeling long-range dependencies and ensuring robustness. To overcome these limitations, we propose a sparse-frame-based spatiotemporal semantic feedback network that incorporates an embedded Sparse Semantic Module (SSM) for structured temporal modeling. The framework leverages forward–backward collaborative refinement and a closed-loop semantic feedback mechanism to achieve implicit inter-frame registration and cross-frame semantic enhancement. While maintaining consistency between training and inference, the method significantly reduces computational overhead and achieves state-of-the-art performance across multiple benchmark datasets, effectively suppressing false alarms and demonstrating superior generalization and robustness.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Machine Learning: Semi-Supervised Learning

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Infrared small target detection (ISTD) under complex backgrounds remains a critical yet challenging task, primarily due to the extremely low signal-to-clutter ratio, persistent dynamic interference, and the lack of distinct target features. While multi-frame detection methods leverages temporal cues to improve upon single-frame approaches, existing methods still struggle with inefficient long-range dependency modeling and insufficient robustness. To overcome these issues, we propose a novel scheme for ISTD, realized through a sparse frames-based spatio-temporal semantic feedback network named FeedbackSTS-Det. The core of our approach is a novel spatio-temporal semantic feedback strategy with a closed-loop semantic association mechanism, which consists of paired forward and backward refinement modules that work cooperatively across the encoder and decoder. Moreover, both modules incorporate an embedded sparse semantic module (SSM), which performs structured sparse temporal modeling to capture long-range dependencies with low computational cost. This integrated design facilitates robust implicit inter-frame registration and continuous semantic refinement, effectively suppressing false alarms. Furthermore, our overall procedure maintains a consistent training-inference pipeline, which ensures reliable performance transfer and increases model robustness. Extensive experiments on multiple benchmark datasets confirm the effectiveness of FeedbackSTS-Det. Code and models are available at: https://github.com/IDIP-Lab/FeedbackSTS-Det.

Problem

• Infrared small target detection
• complex backgrounds
• low signal-to-clutter ratio
• dynamic interference
• long-range dependency

Innovation

• spatio-temporal semantic feedback
• sparse frames
• long-range dependency modeling
• implicit inter-frame registration
• infrared small target detection