PP-YOLOE: An evolved version of YOLO

Xu, Shangliang; Wang, Xinxin; Lv, Wenyu; Chang, Qinyao; Cui, Cheng; Deng, Kaipeng; Wang, Guanzhong; Dang, Qingqing; Wei, Shengyu; Du, Yuning; Lai, Baohua

doi:10.48550/arxiv.2203.16250

Cited by 51 publications

(47 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiment results illustrated in Table 5 fully confirm that the proposed planned re-parameterized model is equally effective on residual-based model. We find that the design of RepCSPResNet [85] also fit our design pattern.…”

Section: Ablation Study 541 Proposed Compound Scaling Methodssupporting

confidence: 61%

“…Currently state-of-the-art real-time object detectors are mainly based on YOLO [61,62,63] and FCOS [76,77], which are [3,79,81,21,54,85,23]. Being able to become a state-of-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [22,97,37,74,59,30,9,45]; (3) a more accurate detection method [76,77,69]; (4) a more robust loss function [96,64,6,56,95,57]; (5) a more efficient label assignment method [99,20,17,82,42]; and (6) a more efficient training method.…”

Section: Related Work 21 Real-time Object Detectorsmentioning

confidence: 99%

See 1 more Smart Citation

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Wang¹,

Bochkovskiy²,

Liao³

2022

Preprint

1,028

707

View full text Add to dashboard Cite

YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100. YOLOv7-E6 object detector (56 FPS V100, 55.9% AP) outperforms both transformer-based detector SWIN-L Cascade-Mask R-CNN (9.2 FPS A100, 53.9% AP) by 509% in speed and 2% in accuracy, and convolutionalbased detector ConvNeXt-XL Cascade-Mask R-CNN (8.6 FPS A100, 55.2% AP) by 551% in speed and 0.7% AP in accuracy, as well as YOLOv7 outperforms: YOLOR, YOLOX, Scaled-YOLOv4, YOLOv5, DETR, Deformable DETR, DINO-5scale-R50, ViT-Adapter-B and many other object detectors in speed and accuracy. Moreover, we train YOLOv7 only on MS COCO dataset from scratch without using any other datasets or pre-trained weights. Source code is released in https:// github.com/ WongKinYiu/ yolov7.

show abstract

Section: Ablation Study 541 Proposed Compound Scaling Methodssupporting

confidence: 61%

Section: Related Work 21 Real-time Object Detectorsmentioning

confidence: 99%

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Wang¹,

Bochkovskiy²,

Liao³

2022

Preprint

1,028

707

View full text Add to dashboard Cite

show abstract

“…We test the speed performance of all official models with FP16-precision on the same Tesla T4 GPU with TensorRT [11]. We compare the upgraded YOLOv6 with YOLOv5 [5], YOLOX [3], PPYOLOE [17], YOLOv7 [16] and YOLOv8 [6]. Note that the performance of YOLOv7-Tiny is re-evaluated according to their open-sourced code and weights at the input size of 416 and 640.…”

Section: Comparisonsmentioning

confidence: 99%

“…YOLOv4 [1] reorganized the detection framework into several separate parts (backbone, neck and head), and verified bag-of-freebies and bag-of-specials at the time to design a framework suitable for training on a single GPU. At present, YOLOv5 [5], YOLOX [3], PPY-OLOE [17], YOLOv7 [16] and most recently YOLOv8 [6] are all the competing candidates for efficient detectors to deploy.…”

Section: Introductionmentioning

confidence: 99%

YOLOv6 v3.0: A Full-Scale Reloading

Li¹,

Li²,

Geng³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The deployment of efficient convolutional neural networks (CNNs) enabled immense progress [4,9,23,[28][29][30]40] in vision detectors for edge devices, in which they consistently reduce parameters and speed counts for improving accuracy. However, these metrics are not correlated well with the efficiency of the models in terms of energy.…”

Section: Introductionmentioning

confidence: 99%

FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs

Tu¹,

Xie²,

Liu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Efficient detectors for edge devices are often optimized for metrics like parameters or speed counts, which remain weak correlation with the energy of detectors. However, among vision applications of convolutional neural networks (CNNs), some, such as always-on surveillance cameras, are critical for energy constraints. This paper aims to serve as a baseline by designing detectors to reach tradeoffs between energy and performance from two perspectives: 1) We extensively analyze various CNNs to identify low-energy architectures, including the selection of activation functions, convolutions operators, and feature fusion structures on necks. These underappreciated details in past works seriously affect the energy consumption of detectors; 2) To break through the dilemmatic energy-performance problem, we propose a balanced detector driven by energy using discovered low-energy components named FemtoDet. In addition to the novel construction, we further improve FemtoDet by considering convolutions and training strategy optimizations. Specifically, we develop a new instance boundary enhancement (IBE) module for convolution optimization to overcome the contradiction between the limited capacity of CNNs and detection tasks in diverse spatial representations, and propose a recursive warm-restart (RecWR) for optimizing training strategy to escape the suboptimization of light-weight detectors, considering the data shift produced in popular augmentations. As a result, Fem-toDet with only 68.77k parameters achieves a competitive score of 46.3 AP50 on PASCAL VOC and power of 7.83W on RTX 3090. Extensive experiments on COCO and TJU-DHD datasets indicate that the proposed method achieves competitive results in diverse scenes.

show abstract

PP-YOLOE: An evolved version of YOLO

Cited by 51 publications

References 23 publications

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

YOLOv6 v3.0: A Full-Scale Reloading

FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs

Contact Info

Product

Resources

About