PP-YOLOE: An evolved version of YOLO

By Shangliang Xu, Xinxin Wang, Wenyu Lv, Qinyao Chang, Cheng Cui, Kaipeng Deng, Guanzhong Wang, Qingqing Dang, Shengyun Wei, Yuning Du and 1 more. arXiv.org, 2022

446 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/5f85aec081f4ee224441899b6c1ceec1535bd58f

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications (2022, methodology): “YOLOv6-L is 2.8%/1.1% more accurate than YOLOX-L/PPYOLOE-L under the same latency constraint.”
Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism (2023, methodology): “To compare our Gold-YOLO with other state-of-the-art detectors in the YOLO series, such as YOLOv5 [13], YOLOX [11], PPYOLOE [52], YOLOv7 [48], YOLOv8 [14] and YOLOv6-3.”
YOLOv10: Real-Time End-to-End Object Detection (2024, methodology): “During training, YOLOs [21, 65, 29, 70] usually leverage TAL [15] to allocate multiple positive samples for each instance.”
A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond (2023, background): “17 PP-YOLO, PP-YOLOv2, and PP-YOLOE PP-YOLO models have been growing parallel to the YOLO models we described.”
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors (2022, methodology): “We ﬁnd that the design of RepCSPResNet [85] also ﬁt our design pattern.”
DETRs Beat YOLOs on Real-time Object Detection (2023, methodology): “We compare RT-DETR with YOLOv5 [10], PP-YOLOE [37], YOLOv6v3.”
YOLOv6 v3.0: A Full-Scale Reloading (2023, methodology): “We compare the upgraded YOLOv6 with YOLOv5 [5], YOLOX [3], PPYOLOE [17], YOLOv7 [16] and YOLOv8 [6].”
YOLO-World: Real-Time Open-Vocabulary Object Detection (2024, background): “Several works [11, 23, 33, 52, 55] propose various architectures or designs for YOLO, including path aggregation networks [29], cross-stage partial networks [51], and re-parameterization [7], which further improve both speed and accuracy.”
Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation (2024, unknown): “T HE YOLO series [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11] stands out as a mainstream method in the realm of object detection, offering several advantages that cater to these diverse applications.”
YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information (2024, methodology): “As for the amount of computation, the best existing models from the smallest to the largest are YOLO MS [7], PP YOLOE [74], and RT DETR [43].”
RTMDet: An Empirical Study of Designing Real-Time Object Detectors (2022, methodology): “(c) Bottleneck block of PPYOLO-E [84] that uses re-parameterized convolution.”
DAMO-YOLO : A Report on Real-Time Object Detection Design (2022, methodology): “In recent advancements of object detection, decoupled head is widely used [9, 17, 37].”