Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark

Abstract

Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels. State-of-the-art object detectors do not provide satisfactory results on tiny objects due to the lack of supervision from discriminative features. Our key observation is that the Intersection over Union (IoU) metric and its extensions are very sensitive to the location deviation of the tiny objects, which drastically deteriorates the quality of label assignment when used in anchor-based detectors. To tackle this problem, we propose a new evaluation metric dubbed Normalized Wasserstein Distance (NWD) and a new RanKing-based Assigning (RKA) strategy for tiny object detection. The proposed NWD-RKA strategy can be easily embedded into all kinds of anchor-based detectors to replace the standard IoU threshold-based one, significantly improving label assignment and providing sufficient supervision information for network training. Tested on four datasets, NWD-RKA can consistently improve tiny object detection performance by a large margin. Besides, observing prominent noisy labels in the Tiny Object Detection in Aerial Images (AI-TOD) dataset, we are motivated to meticulously relabel it and release AI-TOD-v2 and its corresponding benchmark. In AI-TOD-v2, the missing annotation and location error problems are considerably mitigated, facilitating more reliable training and validation processes. Embedding NWD-RKA into DetectoRS, the detection performance achieves 4.3 AP points improvement over state-of-the-art competitors on AI-TOD-v2. Datasets, codes, and more visualizations are available at: https://chasel-tsui.github.io/AI-TOD-v2/

arXiv commentAccepted by ISPRS Journal of Photogrammetry and Remote Sensing

References in corpus (7)

• SSD: Single Shot MultiBox Detector
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• FoveaBox: Beyond Anchor-based Object Detector
• Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
• R${}^2$-CNN: Fast Tiny Object Detection in Large-Scale Remote Sensing Images
• Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss

Cited by in corpus (7)

• Towards Large-Scale Small Object Detection: Survey and Benchmarks
• OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images
• Triple-domain Feature Learning with Frequency-aware Memory Enhancement for Moving Infrared Small Target Detection
• MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results
• Gaussian Combined Distance: A Generic Metric for Object Detection
• RFWNet: A Lightweight Remote Sensing Object Detector Integrating Multiscale Receptive Fields and Foreground Focus Mechanism
• MSG-Loc: Multi-Label Likelihood-based Semantic Graph Matching for Object-Level Global Localization