# TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios

arXiv: https://arxiv.org/abs/2108.11539 · HTML: https://mlsanity.com/paper/2108.11539/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 62 references that are in the map.
- First posted on arXiv 26 Aug 2021.

## Builds on (most cited first, 30 of 48)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [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)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)

## Built on by (most cited first, 30 of 83)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [Efficient Multi-Scale Attention Module with Cross-Spatial Learning](https://mlsanity.com/paper/2305.13563/) (2023)
- [Understanding the Role of the Projector in Knowledge Distillation](https://mlsanity.com/paper/2303.11098/) (2023)
- [Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?](https://mlsanity.com/paper/2312.04548/) (2023)
- [RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning](https://mlsanity.com/paper/2409.13366/) (2024)
- [Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generation](https://mlsanity.com/paper/2306.02651/) (2023)
- [TransVisDrone: Spatio-Temporal Transformer for Vision-based Drone-to-Drone Detection in Aerial Videos](https://mlsanity.com/paper/2210.08423/) (2022)
- [HIC-YOLOv5: Improved YOLOv5 For Small Object Detection](https://mlsanity.com/paper/2309.16393/) (2023)
- [A Region-Based Deep Learning Approach to Automated Retail Checkout](https://mlsanity.com/paper/2204.08584/) (2022)
- [Global-Local MAV Detection under Challenging Conditions based on Appearance and Motion](https://mlsanity.com/paper/2312.11008/) (2023)
- [Vision-Based Environmental Perception for Autonomous Driving](https://mlsanity.com/paper/2212.11453/) (2022)
- [Enhanced Self-Checkout System for Retail Based on Improved YOLOv10](https://mlsanity.com/paper/2407.21308/) (2024)
- [Differential Evolution based Dual Adversarial Camouflage: Fooling Human Eyes and Object Detectors](https://mlsanity.com/paper/2210.08870/) (2022)
- [YOLO-TS: Real-Time Traffic Sign Detection with Enhanced Accuracy Using Optimized Receptive Fields and Anchor-Free Fusion](https://mlsanity.com/paper/2410.17144/) (2024)
- [Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlook](https://mlsanity.com/paper/2505.00630/) (2025)
- [Automatic Cattle Identification using YOLOv5 and Mosaic Augmentation: A Comparative Analysis](https://mlsanity.com/paper/2210.11939/) (2022)
- [Cross-Domain Car Detection Model with Integrated Convolutional Block Attention Mechanism](https://mlsanity.com/paper/2305.20055/) (2023)
- [A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network](https://mlsanity.com/paper/2403.03739/) (2024)
- [E3-UAV: An Edge-based Energy-Efficient Object Detection System for Unmanned Aerial Vehicles](https://mlsanity.com/paper/2308.04774/) (2023)
- [MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World](https://mlsanity.com/paper/2312.17431/) (2023)
- [Vision-Based Anti Unmanned Aerial Technology: Opportunities and Challenges](https://mlsanity.com/paper/2507.10006/) (2025)
- [Defect Detection in Synthetic Fibre Ropes using Detectron2 Framework](https://mlsanity.com/paper/2309.01469/) (2023)
- [Real-Time Detection for Small UAVs: Combining YOLO and Multi-frame Motion Analysis](https://mlsanity.com/paper/2411.02582/) (2024)
- [Evaluation of YOLO Models with Sliced Inference for Small Object Detection](https://mlsanity.com/paper/2203.04799/) (2022)
- [FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications](https://mlsanity.com/paper/2209.03157/) (2022)
- [Advanced Audio Aid for Blind People](https://mlsanity.com/paper/2212.00004/) (2022)
- [Uncertainty-Aware Gradient Stabilization for Small Object Detection](https://mlsanity.com/paper/2303.01803/) (2023)
- [High-order Spatial Interactions Enhanced Lightweight Model for Optical Remote Sensing Image-based Small Ship Detection](https://mlsanity.com/paper/2304.03812/) (2023)
- [Motion-guided small MAV detection in complex and non-planar scenes](https://mlsanity.com/paper/2410.10527/) (2024)

## Abstract (arXiv)

Object detection on drone-captured scenarios is a recent popular task. As drones always navigate in different altitudes, the object scale varies violently, which burdens the optimization of networks. Moreover, high-speed and low-altitude flight bring in the motion blur on the densely packed objects, which leads to great challenge of object distinction. To solve the two issues mentioned above, we propose TPH-YOLOv5. Based on YOLOv5, we add one more prediction head to detect different-scale objects. Then we replace the original prediction heads with Transformer Prediction Heads (TPH) to explore the prediction potential with self-attention mechanism. We also integrate convolutional block attention model (CBAM) to find attention region on scenarios with dense objects. To achieve more improvement of our proposed TPH-YOLOv5, we provide bags of useful strategies such as data augmentation, multiscale testing, multi-model integration and utilizing extra classifier. Extensive experiments on dataset VisDrone2021 show that TPH-YOLOv5 have good performance with impressive interpretability on drone-captured scenarios. On DET-test-challenge dataset, the AP result of TPH-YOLOv5 are 39.18%, which is better than previous SOTA method (DPNetV3) by 1.81%. On VisDrone Challenge 2021, TPHYOLOv5 wins 5th place and achieves well-matched results with 1st place model (AP 39.43%). Compared to baseline model (YOLOv5), TPH-YOLOv5 improves about 7%, which is encouraging and competitive.