YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

计算机科学 人工智能 人机交互
作者
Chien-Yao Wang,I-Hau Yeh,Hong-Yuan Mark Liao
出处
期刊:Cornell University - arXiv 被引量:90
标识
DOI:10.48550/arxiv.2402.13616
摘要

Today's deep learning methods focus on how to design the most appropriate objective functions so that the prediction results of the model can be closest to the ground truth. Meanwhile, an appropriate architecture that can facilitate acquisition of enough information for prediction has to be designed. Existing methods ignore a fact that when input data undergoes layer-by-layer feature extraction and spatial transformation, large amount of information will be lost. This paper will delve into the important issues of data loss when data is transmitted through deep networks, namely information bottleneck and reversible functions. We proposed the concept of programmable gradient information (PGI) to cope with the various changes required by deep networks to achieve multiple objectives. PGI can provide complete input information for the target task to calculate objective function, so that reliable gradient information can be obtained to update network weights. In addition, a new lightweight network architecture -- Generalized Efficient Layer Aggregation Network (GELAN), based on gradient path planning is designed. GELAN's architecture confirms that PGI has gained superior results on lightweight models. We verified the proposed GELAN and PGI on MS COCO dataset based object detection. The results show that GELAN only uses conventional convolution operators to achieve better parameter utilization than the state-of-the-art methods developed based on depth-wise convolution. PGI can be used for variety of models from lightweight to large. It can be used to obtain complete information, so that train-from-scratch models can achieve better results than state-of-the-art models pre-trained using large datasets, the comparison results are shown in Figure 1. The source codes are at: https://github.com/WongKinYiu/yolov9.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
zgx发布了新的文献求助10
3秒前
i2stay完成签到,获得积分10
3秒前
馒头完成签到,获得积分10
5秒前
MS903完成签到,获得积分10
10秒前
CJW完成签到 ,获得积分10
11秒前
韧迹完成签到 ,获得积分0
11秒前
mmd完成签到 ,获得积分10
11秒前
七一安完成签到 ,获得积分10
12秒前
浪麻麻完成签到 ,获得积分10
16秒前
包容的剑完成签到 ,获得积分10
20秒前
等待的大炮完成签到,获得积分10
20秒前
注水萝卜完成签到 ,获得积分10
22秒前
Chem34完成签到,获得积分10
30秒前
32秒前
量子星尘发布了新的文献求助10
32秒前
hhh2018687完成签到,获得积分10
32秒前
32秒前
33秒前
33秒前
33秒前
33秒前
34秒前
34秒前
34秒前
34秒前
34秒前
34秒前
34秒前
嘒彼小星完成签到 ,获得积分10
34秒前
34秒前
35秒前
35秒前
35秒前
35秒前
36秒前
ri_290完成签到,获得积分10
36秒前
37秒前
nsc发布了新的文献求助30
39秒前
nsc发布了新的文献求助10
39秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038039
求助须知:如何正确求助?哪些是违规求助? 3575756
关于积分的说明 11373782
捐赠科研通 3305574
什么是DOI,文献DOI怎么找? 1819239
邀请新用户注册赠送积分活动 892655
科研通“疑难数据库(出版商)”最低求助积分说明 815022