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

arXiv: https://arxiv.org/abs/2206.13996 · HTML: https://mlsanity.com/paper/2206.13996/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 76 references that are in the map.
- First posted on arXiv 28 Jun 2022.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [RepPoints: Point Set Representation for Object Detection](https://mlsanity.com/paper/1904.11490/) (2019)
- [DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution](https://mlsanity.com/paper/2006.02334/) (2020)
- [Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges](https://mlsanity.com/paper/2102.12219/) (2021)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Learning to Learn from Noisy Labeled Data](https://mlsanity.com/paper/1812.05214/) (2018)
- [Scale-Aware Trident Networks for Object Detection](https://mlsanity.com/paper/1901.01892/) (2019)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Probabilistic Anchor Assignment with IoU Prediction for Object Detection](https://mlsanity.com/paper/2007.08103/) (2020)
- [xView: Objects in Context in Overhead Imagery](https://mlsanity.com/paper/1802.07856/) (2018)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)
- [Single-Shot Refinement Neural Network for Object Detection](https://mlsanity.com/paper/1711.06897/) (2017)

## Built on by (most cited first, 30 of 56)

- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection](https://mlsanity.com/paper/2208.08738/) (2022)
- [Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection](https://mlsanity.com/paper/2304.08876/) (2023)
- [DQ-DETR: DETR with Dynamic Query for Tiny Object Detection](https://mlsanity.com/paper/2404.03507/) (2024)
- [Remote Sensing Object Detection Meets Deep Learning: A Meta-review of Challenges and Advances](https://mlsanity.com/paper/2309.06751/) (2023)
- [Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?](https://mlsanity.com/paper/2312.04548/) (2023)
- [Triple-domain Feature Learning with Frequency-aware Memory Enhancement for Moving Infrared Small Target Detection](https://mlsanity.com/paper/2406.06949/) (2024)
- [A DeNoising FPN With Transformer R-CNN for Tiny Object Detection](https://mlsanity.com/paper/2406.05755/) (2024)
- [YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images](https://mlsanity.com/paper/2404.06180/) (2024)
- [CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos](https://mlsanity.com/paper/2406.01029/) (2024)
- [OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images](https://mlsanity.com/paper/2304.11805/) (2023)
- [MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results](https://mlsanity.com/paper/2307.09143/) (2023)
- [Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection](https://mlsanity.com/paper/2505.05741/) (2025)
- [Similarity Distance-Based Label Assignment for Tiny Object Detection](https://mlsanity.com/paper/2407.02394/) (2024)
- [Enhancing Maritime Situational Awareness through End-to-End Onboard Raw Data Analysis](https://mlsanity.com/paper/2411.03403/) (2024)
- [Robust Tiny Object Detection in Aerial Images amidst Label Noise](https://mlsanity.com/paper/2401.08056/) (2024)
- [Rethinking Intersection Over Union for Small Object Detection in Few-Shot Regime](https://mlsanity.com/paper/2307.09562/) (2023)
- [Shape-IoU: More Accurate Metric considering Bounding Box Shape and Scale](https://mlsanity.com/paper/2312.17663/) (2023)
- [Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning](https://mlsanity.com/paper/2412.11582/) (2024)
- [Multimodal Transformer Using Cross-Channel attention for Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2310.13876/) (2023)
- [NBBOX: Noisy Bounding Box Improves Remote Sensing Object Detection](https://mlsanity.com/paper/2409.09424/) (2024)
- [AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection](https://mlsanity.com/paper/2505.15184/) (2025)
- [D3R-DETR: DETR with Dual-Domain Density Refinement for Tiny Object Detection in Aerial Images](https://mlsanity.com/paper/2601.02747/) (2026)
- [UAVDB: Point-Guided Masks for UAV Detection and Segmentation](https://mlsanity.com/paper/2409.06490/) (2024)
- [Interactive Masked Image Modeling for Multimodal Object Detection in Remote Sensing](https://mlsanity.com/paper/2409.08885/) (2024)
- [Analysis of Object Detection Models for Tiny Object in Satellite Imagery: A Dataset-Centric Approach](https://mlsanity.com/paper/2412.10453/) (2024)
- [MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection](https://mlsanity.com/paper/2506.12697/) (2025)
- [Combining Transformers and CNNs for Efficient Object Detection in High-Resolution Satellite Imagery](https://mlsanity.com/paper/2507.11040/) (2025)
- [PRNet: Original Information Is All You Have](https://mlsanity.com/paper/2510.09531/) (2025)
- [Gaussian Combined Distance: A Generic Metric for Object Detection](https://mlsanity.com/paper/2510.27649/) (2025)

## Abstract (arXiv)

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/