• Corpus ID: 236088010

YOLOX: Exceeding YOLO Series in 2021

  title={YOLOX: Exceeding YOLO Series in 2021},
  author={Zheng Ge and Songtao Liu and Feng Wang and Zeming Li and Jian Sun},
In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector — YOLOX. We switch the YOLO detector to an anchor-free manner and conduct other advanced detection techniques, i.e., a decoupled head and the leading label assignment strategy SimOTA to achieve state-of-the-art results across a large scale range of models: For YOLONano with only 0.91M parameters and 1.08G FLOPs, we get 25.3% AP on COCO, surpassing NanoDet by 1.8% AP; for YOLOv3, one… 

Figures and Tables from this paper

PP-YOLOE: An evolved version of YOLO

PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment is presented, using anchor-free paradigm, more pow-erful backbone and neck equipped with CSPRepResStage, ET-head and dynamic label assignment algorithm TAL.

YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6

YOLOX-PAI, an improved version of YOLOX, and an easy use for PAI-Blade which is used to accelerate the inference process based on BladeDISC and TensorRT are added to the all-in-one computer vision tool-box named EasyCV.

YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications

Considering the diverse requirements for speed and accuracy in the real environment, this report extensively examine the up-to-date object detection advancements either from industry or academy and builds a suite of deployment* ready networks at various scales to accommodate diversi-fied use cases.

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

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

Surface Defect Detection with Modified Real-Time Detector YOLOv3

The modified YOLOv3 net achieves the best performance on six types of surface defects in DAGM 2007 dataset, and the pruning ratio is determined by the tradeoff between detecting accuracy and computational efficiency.

PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices

This work creates a new family of real-time object detectors, named PP-PicoDet, which achieves superior performance on object detection for mobile devices and achieves better trade-offs between accuracy and latency compared to other popular models.

Algorithm of Computer Mainboard Quality Detection for Real-Time Based on QD-YOLO

QD-YOLO, an attention-based method to enhance quality-detection efficiency on computer mainboards, is proposed with a composite attention module for the network’s backbone to highlight appropriate feature channels and improve the feature fusion structure, allowing the network to concentrate on the crucial information in the feature map.

You Should Look at All Objects

This paper first re-visits FPN in the detection framework and reveals the nature of the success of FPN from the perspective of optimization, and points out that the degraded performance of large-scale objects is due to the arising of improper back-propagation paths after integrating FPN.

DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

DINO improves over previous DETR-like models in performance and efficiency by using a contrastive way for denoising training, a mixed query selection method for anchor initialization, and a look forward twice scheme for box prediction.

H-YoLov3: High performance object detection applied to assisted driving

  • L. LiX. Li
  • Computer Science
    2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)
  • 2022
The FM module and the method of gradually increasing feature channel number with the perceptual field are proposed to redesign the feature extraction network and constructing a neck of integrating target and environment using depthwise separable convolution is constructed.



YOLO9000: Better, Faster, Stronger

YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories, is introduced and a method to jointly train on object detection and classification is proposed, both novel and drawn from prior work.

PP-YOLOv2: A Practical Object Detector

A collection of existing refinements are comprehensively evaluated to improve the performance of PP-YOLO while almost keep the infer time unchanged and a significant margin of performance has been made.

YOLOv3: An Incremental Improvement

We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more

Scaled-YOLOv4: Scaling Cross Stage Partial Network

We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while maintaining optimal speed and accuracy.

You Only Look One-level Feature

This paper revisits feature pyramids networks (FPN) for one-stage detectors and points out that the success of FPN is due to its divide-and-conquer solution to the optimization problem in object

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

This paper empirically show that on the ImageNet dataset large minibatches cause optimization difficulties, but when these are addressed the trained networks exhibit good generalization and enable training visual recognition models on internet-scale data with high efficiency.

YOLOv4: Optimal Speed and Accuracy of Object Detection

This work uses new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, C mBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100.

You Only Look Once: Unified, Real-Time Object Detection

Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

EfficientDet: Scalable and Efficient Object Detection

This paper systematically study neural network architecture design choices for object detection and proposes a weighted bi-directional feature pyramid network (BiFPN) and a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time.

Object Detection Made Simpler by Eliminating Heuristic NMS

We show a simple NMS-free, end-to-end object detection framework, of which the network is a minimal modification to a one-stage object detector such as the FCOS detection model [24]. We attain on par