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

By Xingkui Zhu, Shuchang Lyu, Xu Wang, Qi Zhao. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021

1,732 citations recorded by the source corpus.

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, multi-scale 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, TPH-YOLOv5 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/129bf8f4a1c9693ba140da7591293b9808c61a4e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jyoti Prakash Sahoo
2. Yisheng Song
3. Ting-Yuan Wang
4. Subrota Kumar Mondal
5. Puyu Cai

In Computer Vision and Pattern Recognition

1. Pengyu Guo
2. Jyoti Prakash Sahoo
3. Yisheng Song
4. Jian Zhan
5. Su He
6. Guo-Liang Zhang
7. Ting-Yuan Wang
8. M.L. Luo

Citations in the corpus

• A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, methodology): “In FSL object detection, most of the work is based on improvements to the original models, such as Faster R-CNN [245] and YOLO [246].”
• Efficient Multi-Scale Attention Module with Cross-Spatial Learning (2023, background): “0) [30] and integrate EMA into prediction branch to achieve the purpose of exploring the prediction potential with self-attention mechanism.”
• FFCA-YOLO for Small Object Detection in Remote Sensing Images (2024, methodology): “At present, some improved YOLO algorithms for object detection in remote sensing have emerged, such as TPH-YOLO [22], FE-YOLO [23], and CA-YOLO [24].”