PP-YOLO: An Effective and Efficient Implementation of Object Detector

Abstract

Object detection is one of the most important areas in computer vision, which plays a key role in various practical scenarios. Due to limitation of hardware, it is often necessary to sacrifice accuracy to ensure the infer speed of the detector in practice. Therefore, the balance between effectiveness and efficiency of object detector must be considered. The goal of this paper is to implement an object detector with relatively balanced effectiveness and efficiency that can be directly applied in actual application scenarios, rather than propose a novel detection model. Considering that YOLOv3 has been widely used in practice, we develop a new object detector based on YOLOv3. We mainly try to combine various existing tricks that almost not increase the number of model parameters and FLOPs, to achieve the goal of improving the accuracy of detector as much as possible while ensuring that the speed is almost unchanged. Since all experiments in this paper are conducted based on PaddlePaddle, we call it PP-YOLO. By combining multiple tricks, PP-YOLO can achieve a better balance between effectiveness (45.2% mAP) and efficiency (72.9 FPS), surpassing the existing state-of-the-art detectors such as EfficientDet and YOLOv4.Source code is at https://github.com/PaddlePaddle/PaddleDetection.

References in corpus (11)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• YOLOv3: An Incremental Improvement
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• DSSD : Deconvolutional Single Shot Detector
• DropBlock: A regularization method for convolutional networks
• Learning Spatial Fusion for Single-Shot Object Detection
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• FreeAnchor: Learning to Match Anchors for Visual Object Detection
• Soft Anchor-Point Object Detection
• Multiple Anchor Learning for Visual Object Detection

Cited by in corpus (8)

• Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information
• Scaled-YOLOv4: Scaling Cross Stage Partial Network
• A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects
• PP-YOLOv2: A Practical Object Detector
• Domain Adaptive YOLO for One-Stage Cross-Domain Detection
• ODOR: The ICPR2022 ODeuropa Challenge on Olfactory Object Recognition
• PAFNet: An Efficient Anchor-Free Object Detector Guidance
• DynaDog+T: A Parametric Animal Model for Synthetic Canine Image Generation