Today’s deep learning methods focus on designing the most suitable objective function so that the model’s prediction results are closest to the actual situation. At the same time, a suitable architecture must be designed to obtain sufficient information for prediction. Existing methods ignore the fact that when the input data undergoes layer-by-layer feature extraction and spatial transformation, a large amount of information will be lost. This article will delve into important issues when transmitting data through deep networks, namely information bottlenecks and reversible functions. Based on this, the concept of programmable gradient information (PGI) is proposed to cope with the various changes required by deep networks to achieve multi-objectives. PGI can provide complete input information for the target task to calculate the objective function, thereby obtaining reliable gradient information to update network weights. In addition, a new lightweight network architecture-Generalized Efficient Layer Aggregation Network (GELAN) based on gradient path planning is designed.
The verification results show that the GELAN architecture has gained significant advantages through PGI on lightweight models. Experiments on the MS COCO data set show that GELAN combined with PGI can achieve better parameter utilization than the state-of-the-art methods based on deep convolution using only traditional convolution operators. PGI's versatility makes it suitable for a wide range of models, from lightweight to large models. With PGI, the model is fully informed, so it is possible to achieve better results using a model trained from scratch than a state-of-the-art model pre-trained on a large dataset.
Article address: https://arxiv.org/pdf/2402.13616
Code link: https://github.com/WongKinYiu/yolov9
Excellent Performance
According to the comparison results of real-time target detectors on the MS COCO dataset, the target detection methods based on GELAN and PGI are significantly ahead of the previous methods trained from scratch in terms of target detection performance. The new method outperforms RT DETR, which relies on large dataset pre-training, in terms of accuracy, and also outperforms YOLO MS based on deep convolution design in terms of parameter utilization. These results indicate that GELAN and PGI methods have potential advantages in the field of target detection and may become important technology choices in future research and applications.
Contributions of this article
- The existing deep neural network architecture is theoretically analyzed from the perspective of reversible functions. Through this This process has successfully explained many phenomena that were difficult to explain in the past. PGI and auxiliary reversible branches were also designed based on this analysis and achieved excellent results. The PGI designed by
- solves the problem that deep supervision can only be used for extremely deep neural network architectures, making the new lightweight architecture truly applicable to daily work.
- The designed GELAN uses only traditional convolutions to achieve higher parameter usage than deep convolution designs based on state-of-the-art technology, while showing great advantages of being lightweight, fast and accurate.
- Combining the proposed PGI and GELAN, the object detection performance of YOLOv9 on the MS COCO dataset greatly exceeds existing real-time object detectors in all aspects.
Method
PGI and related network architecture and methods
As shown in the figure below, (a) Path Aggregation Network (PAN), (b) Reversible Column (RevCol), (c) traditional deep supervision, and (d) Programmable Gradient Information (PGI) proposed by YOLOv9.
PGI is mainly composed of three components:
- Main branch: the architecture used for inference;
- Auxiliary reversible Branch: Generate reliable gradients for the main branch to transmit backward;
- Multi-level auxiliary information: Control the main branch to learn planable multi-level semantic information.
The architecture of GELAN
As shown in the figure below, (a) CSPNet, (b) ELAN, and (c) GELAN proposed by YOLOv9. It imitates CSPNet and extends ELAN to GELAN, which can support any computing block.
Comparison of results
Comparison with existing technology
The following table lists A comparison of YOLOv9 with other real-time object detectors trained from scratch is presented. Overall, the best performing methods among existing methods are YOLO MS-S for lightweight models, YOLO MS for medium models, YOLOv7 AF for general models, and YOLOv8-X for large models. Compared with YOLO MS of lightweight and medium models, YOLOv9 has about 10% fewer parameters and 5∼15% less calculations, but still has a 0.4∼0.6% improvement in AP. Compared with YOLOv7 AF, YOLOv9-C has 42% fewer parameters and 21% fewer calculations, but achieves the same AP (53%). Compared with YOLOv8-X, YOLOv9-X has 15% fewer parameters, 25% fewer calculations, and a significant improvement in AP, which has increased by 1.7%. The above comparison results show that YOLOv9 is significantly improved over existing methods in all aspects.
Comparison with the most advanced real-time object detectors
The methods participating in the comparison all use ImageNet as pre-training weights, including RT DETR, RTMDet and PP-YOLOE, etc. YOLOv9 using the scratch training method clearly exceeds the performance of other methods.
Visualized results
Feature map (visualized results): By PlainNet , Random initial weight output of ResNet, CSPNet and GELAN at different depths. After 100 layers, ResNet starts to produce feed-forward output that is enough to confuse the target information. The GELAN proposed here can still retain quite complete information at the 150th layer, and still has sufficient discrimination ability at the 200th layer.
PAN feature maps (visualization results) of GELAN and YOLOv9 (GELAN PGI): After a round of bias warm-up. GELAN had some initial divergence, but after adding the reversible branch of PGI, it was better able to focus on the target object.
Visualized results of random initial weight output feature maps of different network architectures: (a) Input image, (b) PlainNet, (c) ResNet, (d) CSPNet and (e) proposed GELAN. As can be seen from the figure, in different architectures, the degree of information provided to calculate the loss of the objective function is different, and our architecture can retain the most complete information and provide the most reliable gradient information for calculating the objective function.
Conclusion
This paper proposes to use PGI to solve the problem of information bottlenecks and deep supervision mechanisms that are not suitable for lightweight neural networks. question. designed GELAN, an efficient and lightweight neural network. In terms of target detection, GELAN shows strong and stable performance under different computing modules and depth settings. It is indeed broadly scalable to models suitable for a variety of inference devices. In response to the above two problems, the introduction of PGI enables both lightweight models and deep models to achieve significant improvements in accuracy. YOLOv9, designed by combining PGI and GELAN, shows strong competitiveness. Its excellent design allows the deep model to reduce the number of parameters by 49% and the calculation amount by 43% compared with YOLOv8, but still achieves a 0.6% AP improvement on the MS COCO data set.
Original link: https://mp.weixin.qq.com/s/nP4JzVwn1S-MeKAzbf97uw
The above is the detailed content of YOLO is immortal! YOLOv9 is released: performance and speed SOTA~. For more information, please follow other related articles on the PHP Chinese website!

近年来,图神经网络(GNN)取得了快速、令人难以置信的进展。图神经网络又称为图深度学习、图表征学习(图表示学习)或几何深度学习,是机器学习特别是深度学习领域增长最快的研究课题。本次分享的题目为《GNN的基础、前沿和应用》,主要介绍由吴凌飞、崔鹏、裴健、赵亮几位学者牵头编撰的综合性书籍《图神经网络基础、前沿与应用》中的大致内容。一、图神经网络的介绍1、为什么要研究图?图是一种描述和建模复杂系统的通用语言。图本身并不复杂,它主要由边和结点构成。我们可以用结点表示任何我们想要建模的物体,可以用边表示两

当前主流的AI芯片主要分为三类,GPU、FPGA、ASIC。GPU、FPGA均是前期较为成熟的芯片架构,属于通用型芯片。ASIC属于为AI特定场景定制的芯片。行业内已经确认CPU不适用于AI计算,但是在AI应用领域也是必不可少。 GPU方案GPU与CPU的架构对比CPU遵循的是冯·诺依曼架构,其核心是存储程序/数据、串行顺序执行。因此CPU的架构中需要大量的空间去放置存储单元(Cache)和控制单元(Control),相比之下计算单元(ALU)只占据了很小的一部分,所以CPU在进行大规模并行计算

在我的世界(Minecraft)中,红石是一种非常重要的物品。它是游戏中的一种独特材料,开关、红石火把和红石块等能对导线或物体提供类似电流的能量。红石电路可以为你建造用于控制或激活其他机械的结构,其本身既可以被设计为用于响应玩家的手动激活,也可以反复输出信号或者响应非玩家引发的变化,如生物移动、物品掉落、植物生长、日夜更替等等。因此,在我的世界中,红石能够控制的机械类别极其多,小到简单机械如自动门、光开关和频闪电源,大到占地巨大的电梯、自动农场、小游戏平台甚至游戏内建的计算机。近日,B站UP主@

当风大到可以把伞吹坏的程度,无人机却稳稳当当,就像这样:御风飞行是空中飞行的一部分,从大的层面来讲,当飞行员驾驶飞机着陆时,风速可能会给他们带来挑战;从小的层面来讲,阵风也会影响无人机的飞行。目前来看,无人机要么在受控条件下飞行,无风;要么由人类使用遥控器操作。无人机被研究者控制在开阔的天空中编队飞行,但这些飞行通常是在理想的条件和环境下进行的。然而,要想让无人机自主执行必要但日常的任务,例如运送包裹,无人机必须能够实时适应风况。为了让无人机在风中飞行时具有更好的机动性,来自加州理工学院的一组工

1 什么是对比学习1.1 对比学习的定义1.2 对比学习的原理1.3 经典对比学习算法系列2 对比学习的应用3 对比学习在转转的实践3.1 CL在推荐召回的实践3.2 CL在转转的未来规划1 什么是对比学习1.1 对比学习的定义对比学习(Contrastive Learning, CL)是近年来 AI 领域的热门研究方向,吸引了众多研究学者的关注,其所属的自监督学习方式,更是在 ICLR 2020 被 Bengio 和 LeCun 等大佬点名称为 AI 的未来,后陆续登陆 NIPS, ACL,

本文由Cristian Bodnar 和Fabrizio Frasca 合著,以 C. Bodnar 、F. Frasca 等人发表于2021 ICML《Weisfeiler and Lehman Go Topological: 信息传递简单网络》和2021 NeurIPS 《Weisfeiler and Lehman Go Cellular: CW 网络》论文为参考。本文仅是通过微分几何学和代数拓扑学的视角讨论图神经网络系列的部分内容。从计算机网络到大型强子对撞机中的粒子相互作用,图可以用来模

AI面部识别领域又开辟新业务了?这次,是鉴别二战时期老照片里的人脸图像。近日,来自谷歌的一名软件工程师Daniel Patt 研发了一项名为N2N(Numbers to Names)的 AI人脸识别技术,它可识别二战前欧洲和大屠杀时期的照片,并将他们与现代的人们联系起来。用AI寻找失散多年的亲人2016年,帕特在参观华沙波兰裔犹太人纪念馆时,萌生了一个想法。这一张张陌生的脸庞,会不会与自己存在血缘的联系?他的祖父母/外祖父母中有三位是来自波兰的大屠杀幸存者,他想帮助祖母找到被纳粹杀害的家人的照

OTO 是业内首个自动化、一站式、用户友好且通用的神经网络训练与结构压缩框架。 在人工智能时代,如何部署和维护神经网络是产品化的关键问题考虑到节省运算成本,同时尽可能小地损失模型性能,压缩神经网络成为了 DNN 产品化的关键之一。DNN 压缩通常来说有三种方式,剪枝,知识蒸馏和量化。剪枝旨在识别并去除冗余结构,给 DNN 瘦身的同时尽可能地保持模型性能,是最为通用且有效的压缩方法。三种方法通常来讲可以相辅相成,共同作用来达到最佳的压缩效果。然而现存的剪枝方法大都只针对特定模型,特定任务,且需要很


Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

AI Hentai Generator
Generate AI Hentai for free.

Hot Article

Hot Tools

mPDF
mPDF is a PHP library that can generate PDF files from UTF-8 encoded HTML. The original author, Ian Back, wrote mPDF to output PDF files "on the fly" from his website and handle different languages. It is slower than original scripts like HTML2FPDF and produces larger files when using Unicode fonts, but supports CSS styles etc. and has a lot of enhancements. Supports almost all languages, including RTL (Arabic and Hebrew) and CJK (Chinese, Japanese and Korean). Supports nested block-level elements (such as P, DIV),

ZendStudio 13.5.1 Mac
Powerful PHP integrated development environment

Zend Studio 13.0.1
Powerful PHP integrated development environment

SublimeText3 Chinese version
Chinese version, very easy to use

Safe Exam Browser
Safe Exam Browser is a secure browser environment for taking online exams securely. This software turns any computer into a secure workstation. It controls access to any utility and prevents students from using unauthorized resources.
