MI-DETR: A Strong Baseline for Moving Infrared Small Target Detection with Bio-Inspired Motion Integration

2026-03-05

AI Summary

This work addresses the challenge of detecting infrared small targets, which are difficult to identify due to their extremely small size and low contrast against complex dynamic backgrounds. To this end, the authors propose MI-DETR, a retina-inspired dual-path detection framework that explicitly models both motion and appearance cues without requiring additional motion labels or alignment operations. The core components include a Retina-inspired Cellular Automaton (RCA) for generating motion maps, a Parvo-Magno Interconnection (PMI) module enabling bidirectional interaction and fusion between pathways, and an RT-DETR decoder for detection. Evaluated on three benchmarks—IRDST-H, DAUB-R, and ITSDT-15K—the method achieves mAP@50 scores of 70.3%, 98.0%, and 88.3%, respectively, significantly outperforming existing approaches.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

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
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Infrared small target detection (ISTD) is challenging because tiny, low-contrast targets are easily obscured by complex and dynamic backgrounds. Conventional multi-frame approaches typically learn motion implicitly through deep neural networks, often requiring additional motion supervision or explicit alignment modules. We propose Motion Integration DETR (MI-DETR), a bio-inspired dual-pathway detector that processes one infrared frame per time step while explicitly modeling motion. First, a retina-inspired cellular automaton (RCA) converts raw frame sequences into a motion map defined on the same pixel grid as the appearance image, enabling parvocellular-like appearance and magnocellular-like motion pathways to be supervised by a single set of bounding boxes without extra motion labels or alignment operations. Second, a Parvocellular-Magnocellular Interconnection (PMI) Block facilitates bidirectional feature interaction between the two pathways, providing a biologically motivated intermediate interconnection mechanism. Finally, a RT-DETR decoder operates on features from the two pathways to produce detection results. Surprisingly, our proposed simple yet effective approach yields strong performance on three commonly used ISTD benchmarks. MI-DETR achieves 70.3% mAP@50 and 72.7% F1 on IRDST-H (+26.35 mAP@50 over the best multi-frame baseline), 98.0% mAP@50 on DAUB-R, and 88.3% mAP@50 on ITSDT-15K, demonstrating the effectiveness of biologically inspired motion-appearance integration. Code is available at https://github.com/nliu-25/MI-DETR.

Problem

• Infrared small target detection
• low-contrast targets
• dynamic backgrounds
• motion modeling
• bio-inspired vision

Innovation

• bio-inspired vision
• motion integration
• infrared small target detection
• cellular automaton
• dual-pathway architecture