# CSFPR-RTDETR-CR: A Causal Intervention Enhanced Framework for Infrared UAV Small Target Detection with Feature Debiasing

## TL;DR

This paper introduces a new framework for detecting small targets in infrared UAV images by reducing feature bias and improving detection accuracy using causal reasoning techniques.

## Contribution

The paper proposes a causal intervention-enhanced framework with feature debiasing to improve infrared UAV small target detection.

## Key findings

- The proposed framework improves mAP@50 by 5.6% and mAP@50:95 by 1.8% on the HIT-UAV dataset.
- Visualization analysis confirms enhanced feature discrimination and detection performance.

## Abstract

Infrared UAV small target detection is critical in areas such as military reconnaissance, disaster monitoring, and border patrol. However, it faces challenges due to the small size of targets, weak texture, and complex backgrounds in infrared images. Existing deep learning-based object detection models often learn spurious correlations between targets and their backgrounds. This leads to poor generalization and higher rates of false positives and missed detections in complex scenes. To overcome feature bias and improve performance, this paper proposes an enhanced detection framework based on causal reasoning. The framework builds on the advanced CSFPR-RTDETR detector. Guided by the principles of structural causal models, it explicitly separates causal and non-causal features in the feature space. Feature debiasing is achieved through a three-path approach. First, a causal data augmentation module is introduced. It applies frequency perturbations drawn from a Gaussian distribution to non-causal features. This strengthens the model’s robustness against mixed disturbances. Second, a counterfactual reasoning module is integrated into the backbone network. This module generates counterfactual samples to intervene in the feature distribution, helping the model identify and utilize causal features more effectively. Third, a causal attention mechanism module is added to the encoder. By distinguishing and weighting causal and non-causal features, it guides the model to focus on features that are essential for detecting targets. Experiments on the HIT-UAV public dataset show that the proposed framework improves mAP@50 by 5.6% and mAP@50:95 by 1.8%. Visualization analysis further confirms that the framework enhances feature discrimination and overall detection performance.