PP-YOLOE: An evolved version of YOLO

• URL: http://arxiv.org/abs/2203.16250v1
• Date: Wed, 30 Mar 2022 12:31:39 GMT
• Title: PP-YOLOE: An evolved version of YOLO
• Authors: Shangliang Xu, Xinxin Wang, Wenyu Lv, Qinyao Chang, Cheng Cui, Kaipeng Deng, Guanzhong Wang, Qingqing Dang, Shengyu Wei, Yuning Du, Baohua Lai
• Abstract summary: We present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment. We optimize on the basis of the previous PP-YOLOv2, using anchor-free paradigm, more powerful backbone and neck equipped with CSPRepResStage, ET-head and dynamic label assignment algorithm TAL. As a result, PP-YOLOE-l achieves 51.4 mAP on COCO test-dev and 78.1 FPS on Tesla V100, yielding a remarkable improvement of (+1.9 AP, +13.35% speed up) and (+1.3 AP, +24.96%
• Score: 4.9022682894446685
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this report, we present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment. We optimize on the basis of the previous PP-YOLOv2, using anchor-free paradigm, more powerful backbone and neck equipped with CSPRepResStage, ET-head and dynamic label assignment algorithm TAL. We provide s/m/l/x models for different practice scenarios. As a result, PP-YOLOE-l achieves 51.4 mAP on COCO test-dev and 78.1 FPS on Tesla V100, yielding a remarkable improvement of (+1.9 AP, +13.35% speed up) and (+1.3 AP, +24.96% speed up), compared to the previous state-of-the-art industrial models PP-YOLOv2 and YOLOX respectively. Further, PP-YOLOE inference speed achieves 149.2 FPS with TensorRT and FP16-precision. We also conduct extensive experiments to verify the effectiveness of our designs. Source code and pre-trained models are available at https://github.com/PaddlePaddle/PaddleDetection .

Related papers

• Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think [53.2706196341054]
  We show that the perceived inefficiency was caused by a flaw in the inference pipeline that has so far gone unnoticed. We perform end-to-end fine-tuning on top of the single-step model with task-specific losses and get a deterministic model that outperforms all other diffusion-based depth and normal estimation models.
  arXiv  Detail & Related papers  (2024-09-17T16:58:52Z)
• YOLOv10: Real-Time End-to-End Object Detection [68.28699631793967]
  YOLOs have emerged as the predominant paradigm in the field of real-time object detection. The reliance on the non-maximum suppression (NMS) for post-processing hampers the end-to-end deployment of YOLOs. We introduce the holistic efficiency-accuracy driven model design strategy for YOLOs.
  arXiv  Detail & Related papers  (2024-05-23T11:44:29Z)
• YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection [80.11152626362109]
  We provide an efficient and performant object detector, termed YOLO-MS. We train our YOLO-MS on the MS COCO dataset from scratch without relying on any other large-scale datasets. Our work can also be used as a plug-and-play module for other YOLO models.
  arXiv  Detail & Related papers  (2023-08-10T10:12:27Z)
• EdgeYOLO: An Edge-Real-Time Object Detector [69.41688769991482]
  This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS 2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone 2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia
  arXiv  Detail & Related papers  (2023-02-15T06:05:14Z)
• PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector [14.263912554269435]
  PP-YOLOE-R is an anchor-free rotated object detector based on PP-YOLOE. PP-YOLOE-R-l and PP-YOLOE-R-x achieve 78.14 and 78.28 mAP on DOTA 1.0 dataset with single-scale training and testing. PP-YOLOE-R-x surpasses all anchor-free methods and demonstrates competitive performance to state-of-the-art anchor-based two-stage models.
  arXiv  Detail & Related papers  (2022-11-04T11:38:30Z)
• TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios [19.12254722446651]
  Object detection on drone-captured scenarios is a popular task. High-speed and low-altitude flight bring in the motion blur on the densely packed objects. Based on YOLOv5, we add one more prediction head to detect different-scale objects. We replace the original prediction heads with Transformer Prediction Heads.
  arXiv  Detail & Related papers  (2021-08-26T01:24:15Z)
• Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge [57.647371468876116]
  We introduce our real-time 2D object detection system for the realistic autonomous driving scenario. Our detector is built on a newly designed YOLO model, called YOLOX. On the Argoverse-HD dataset, our system achieves 41.0 streaming AP, which surpassed second place by 7.8/6.1 on detection-only track/fully track, respectively.
  arXiv  Detail & Related papers  (2021-07-27T06:36:06Z)
• YOLOX: Exceeding YOLO Series in 2021 [25.734980783220976]
  We switch the YOLO detector to an anchor-free manner and conduct other advanced detection techniques. For YOLO-Nano with only 0.91M parameters and 1.08G FLOPs, we get 25.3% AP on COCO, surpassing NanoDet by 1.8% AP. For YOLOX-L with roughly the same amount of parameters as YOLOv4-CSP, YOLOv5-L, we achieve 50.0% AP on COCO at a speed of 68.9 FPS on Tesla V100.
  arXiv  Detail & Related papers  (2021-07-18T12:55:11Z)
• PP-YOLOv2: A Practical Object Detector [13.262416549127664]
  We evaluate a collection of existing refinements to improve the performance of PP-YOLO. By combining multiple effective refinements, we boost PP-YOLO's performance from 45.9% mAP to 49.5% mAP. In terms of speed, PP-YOLOv2 runs in 68.9FPS at 640x640 input size.
  arXiv  Detail & Related papers  (2021-04-21T08:55:37Z)
• PP-YOLO: An Effective and Efficient Implementation of Object Detector [44.189808709103865]
  This paper implements an object detector with relatively balanced effectiveness and efficiency. Considering that YOLOv3 has been widely used in practice, we develop a new object detector based on YOLOv3. Since all experiments in this paper are conducted based on PaddlePaddle, we call it PP-YOLO.
  arXiv  Detail & Related papers  (2020-07-23T16:06:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.