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

TL;DR

MI-DETR introduces a biologically inspired dual-pathway neural network that explicitly models motion and appearance for improved infrared small target detection, outperforming existing multi-frame methods without requiring extra motion labels.

Contribution

The paper presents MI-DETR, a novel bio-inspired dual-pathway detector that explicitly models motion and appearance, with a motion map and interconnection mechanism, achieving state-of-the-art results in infrared small target detection.

Findings

Achieves 70.3% mAP@50 on IRDST-H, outperforming baselines by 26.35 points.

Attains 98.0% mAP@50 on DAUB-R, demonstrating high accuracy.

Provides a biologically motivated framework that effectively integrates motion and appearance features.

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.