Exponentially Weighted Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection Model Training in Unmanned Aerial Vehicles Surveillance Scenarios

2025-03-27

AI Summary

In drone-based emergency monitoring, long-tailed class distributions severely degrade detection performance for rare targets (e.g., fire, smoke, personnel). To address this, we propose an exponential instance-aware oversampling strategy that computes sampling weights using the geometric mean of image- and instance-level frequencies, then applies an exponential transformation to amplify emphasis on underrepresented classes. This approach significantly enhances training focus on and discriminability of tail classes, especially for lightweight models. Integrated into the YOLOv11 framework, our method achieves an average 22% mAP improvement over baseline methods across five benchmark datasets—including Fireman-UAV-RGBT—while yielding particularly substantial gains in AP for rare categories. Experimental results demonstrate both effectiveness and generalizability in resource-constrained, real-time aerial monitoring scenarios.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Remote Sensing / Geospatial AI
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

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
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Object detection models often struggle with class imbalance, where rare categories appear significantly less frequently than common ones. Existing sampling-based rebalancing strategies, such as Repeat Factor Sampling (RFS) and Instance-Aware Repeat Factor Sampling (IRFS), mitigate this issue by adjusting sample frequencies based on image and instance counts. However, these methods are based on linear adjustments, which limit their effectiveness in long-tailed distributions. This work introduces Exponentially Weighted Instance-Aware Repeat Factor Sampling (E-IRFS), an extension of IRFS that applies exponential scaling to better differentiate between rare and frequent classes. E-IRFS adjusts sampling probabilities using an exponential function applied to the geometric mean of image and instance frequencies, ensuring a more adaptive rebalancing strategy. We evaluate E-IRFS on a dataset derived from the Fireman-UAV-RGBT Dataset and four additional public datasets, using YOLOv11 object detection models to identify fire, smoke, people and lakes in emergency scenarios. The results show that E-IRFS improves detection performance by 22% over the baseline and outperforms RFS and IRFS, particularly for rare categories. The analysis also highlights that E-IRFS has a stronger effect on lightweight models with limited capacity, as these models rely more on data sampling strategies to address class imbalance. The findings demonstrate that E-IRFS improves rare object detection in resource-constrained environments, making it a suitable solution for real-time applications such as UAV-based emergency monitoring.

Problem

• Addresses class imbalance in long-tailed object detection
• Improves rare category detection in UAV surveillance
• Enhances sampling strategy with exponential weighting

Innovation

• Exponentially weighted sampling for class imbalance
• Adaptive rebalancing with exponential scaling
• Improved rare object detection in UAVs