# HRDNet: High-resolution Detection Network for Small Objects

arXiv: https://arxiv.org/abs/2006.07607 · HTML: https://mlsanity.com/paper/2006.07607/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2020.

## Built on by (most cited first, 25 of 25)

- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery](https://mlsanity.com/paper/2112.10415/) (2021)
- [Deep Learning for UAV-based Object Detection and Tracking: A Survey](https://mlsanity.com/paper/2110.12638/) (2021)
- [ESOD: Efficient Small Object Detection on High-Resolution Images](https://mlsanity.com/paper/2407.16424/) (2024)
- [RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning](https://mlsanity.com/paper/2409.13366/) (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)
- [Archangel: A Hybrid UAV-based Human Detection Benchmark with Position and Pose Metadata](https://mlsanity.com/paper/2209.00128/) (2022)
- [OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images](https://mlsanity.com/paper/2304.11805/) (2023)
- [Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery](https://mlsanity.com/paper/2312.15219/) (2023)
- [Progressive Multi-scale Consistent Network for Multi-class Fundus Lesion Segmentation](https://mlsanity.com/paper/2205.15720/) (2022)
- [EFSI-DETR: Efficient Frequency-Semantic Integration for Real-Time Small Object Detection in UAV Imagery](https://mlsanity.com/paper/2601.18597/) (2026)
- [OS-W2S: An Automatic Labeling Engine for Language-Guided Open-Set Aerial Object Detection](https://mlsanity.com/paper/2505.03334/) (2025)
- [VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection](https://mlsanity.com/paper/2511.18075/) (2025)
- [Generative Spatiotemporal Data Augmentation](https://mlsanity.com/paper/2512.12508/) (2025)
- [Analysis and Adaptation of YOLOv4 for Object Detection in Aerial Images](https://mlsanity.com/paper/2203.10194/) (2022)
- [An advanced YOLOv3 method for small object detection](https://mlsanity.com/paper/2212.02809/) (2022)
- [Enhanced Small Target Detection via Multi-Modal Fusion and Attention Mechanisms: A YOLOv5 Approach](https://mlsanity.com/paper/2504.11262/) (2025)
- [PT-DETR: Small Target Detection Based on Partially-Aware Detail Focus](https://mlsanity.com/paper/2510.26630/) (2025)
- [MLPerf Automotive](https://mlsanity.com/paper/2510.27065/) (2025)
- [Boundary and Position Information Mining for Aerial Small Object Detection](https://mlsanity.com/paper/2601.16617/) (2026)
- [Small Object Detection Model with Spatial Laplacian Pyramid Attention and Multi-Scale Features Enhancement in Aerial Images](https://mlsanity.com/paper/2602.23031/) (2026)
- [DisDop: Distillation with Domain Priors for Open-Vocabulary Aerial Object Detection](https://mlsanity.com/paper/2605.24639/) (2026)
- [FRFDet: Efficient UAV Small Object Detection with Symmetric Sampling and Scalable Fusion](https://mlsanity.com/paper/2607.04125/) (2026)
- [Small-Pollinator Detection in Cluttered Field Video](https://mlsanity.com/paper/2607.22913/) (2026)

## Abstract (arXiv)

Small object detection is challenging because small objects do not contain detailed information and may even disappear in the deep network. Usually, feeding high-resolution images into a network can alleviate this issue. However, simply enlarging the resolution will cause more problems, such as that, it aggravates the large variant of object scale and introduces unbearable computation cost. To keep the benefits of high-resolution images without bringing up new problems, we proposed the High-Resolution Detection Network (HRDNet). HRDNet takes multiple resolution inputs using multi-depth backbones. To fully take advantage of multiple features, we proposed Multi-Depth Image Pyramid Network (MD-IPN) and Multi-Scale Feature Pyramid Network (MS-FPN) in HRDNet. MD-IPN maintains multiple position information using multiple depth backbones. Specifically, high-resolution input will be fed into a shallow network to reserve more positional information and reducing the computational cost while low-resolution input will be fed into a deep network to extract more semantics. By extracting various features from high to low resolutions, the MD-IPN is able to improve the performance of small object detection as well as maintaining the performance of middle and large objects. MS-FPN is proposed to align and fuse multi-scale feature groups generated by MD-IPN to reduce the information imbalance between these multi-scale multi-level features. Extensive experiments and ablation studies are conducted on the standard benchmark dataset MS COCO2017, Pascal VOC2007/2012 and a typical small object dataset, VisDrone 2019. Notably, our proposed HRDNet achieves the state-of-the-art on these datasets and it performs better on small objects.