YOLOv3：小改进大提升的目标检测技术
需积分: 0 170 浏览量
更新于2024-08-04
收藏 2.34MB PDF 举报
本文是一篇关于目标检测领域的研究论文，名为"YOLOv3: An Incremental Improvement"，由Joseph Redmon和Ali Farhadi在华盛顿大学共同撰写。YOLOv3是对前一代YOLO模型的优化升级，旨在提高检测精度和速度。作者提到，虽然论文没有涉及大量的新研究，但通过一系列小的改动，YOLOv3在保持高效率的同时，显著提升了性能。
1. **更新与改进**:
YOLOv3在设计上做了若干微调，包括但不限于网络架构的优化，这使得它在保持实时性（例如，在320x320分辨率下运行速度达到22毫秒，准确率达到28.2 mAP）的同时，比其前辈SSD更准确。特别是在旧的5IOU mAP检测指标下，YOLOv3表现出色，实现了57.9 AP50的精度，仅需51毫秒，相比之下，RetinaNet的57.5 AP50需要198毫秒，这意味着YOLOv3的速度提高了约3.8倍。
2. **速度与准确性**:
论文强调了YOLOv3的双重优势，即使在提高精度的同时，也保持了较高的运行速度。这表明它在实际应用中的实用性得到了提升，尤其是在需要快速响应和高精度场景中。
3. **技术背景**:
作者并未专注于深入理论研究，而是利用了去年的一些研究成果（[12]和[1]），并将这些积累用于改进YOLOv3。他们承认，这些改进并非革命性的，但是一系列的小改进组合起来，带来了整体性能的提升。
4. **代码共享**:
与以往一样，作者公开了所有的代码，以便于社区成员的交流和进一步研究，体现了开放源代码的精神，有助于技术的持续发展和创新。
5. **研究环境**:
训练工作是在TitanX显卡上进行的，这展示了实验的硬件环境，同时也为其他研究人员提供了参考。
YOLOv3论文主要关注的是如何通过增量改进现有的目标检测算法，使其在保持高速度的同时提高检测精度，同时分享开源代码以促进领域内的合作和进步。
YOLOv3: An Incremental Improvement
Joseph Redmon Ali Farhadi
University of Washington
Abstract
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 accurate. It’s still fast though, don’t
worry. At 320 × 320 YOLOv3 runs in 22 ms at 28.2 mAP,
as accurate as SSD but three times faster. When we look
at the old .5 IOU mAP detection metric YOLOv3 is quite
good. It achieves 57.9 AP
50
in 51 ms on a Titan X, com-
pared to 57.5 AP
50
in 198 ms by RetinaNet, similar perfor-
mance but 3.8× faster. As always, all the code is online at
https://pjreddie.com/yolo/.
1. Introduction
Sometimes you just kinda phone it in for a year, you
know? I didn’t do a whole lot of research this year. Spent
a lot of time on Twitter. Played around with GANs a little.
I had a little momentum left over from last year [12] [1]; I
managed to make some improvements to YOLO. But, hon-
estly, nothing like super interesting, just a bunch of small
changes that make it better. I also helped out with other
people’s research a little.
Actually, that’s what brings us here today. We have
a camera-ready deadline [4] and we need to cite some of
the random updates I made to YOLO but we don’t have a
source. So get ready for a TECH REPORT!
The great thing about tech reports is that they don’t need
intros, y’all know why we’re here. So the end of this intro-
duction will signpost for the rest of the paper. First we’ll tell
you what the deal is with YOLOv3. Then we’ll tell you how
we do. We’ll also tell you about some things we tried that
didn’t work. Finally we’ll contemplate what this all means.
2. The Deal
So here’s the deal with YOLOv3: We mostly took good
ideas from other people. We also trained a new classifier
network that’s better than the other ones. We’ll just take
you through the whole system from scratch so you can un-
derstand it all.
50 100 150 200 250
inference time (ms)
28
30
32
34
36
38
COCO AP
B C
D
E
F
G
RetinaNet-50
RetinaNet-101
YOLOv3
Method
[B] SSD321
[C] DSSD321
[D] R-FCN
[E] SSD513
[F] DSSD513
[G] FPN FRCN
RetinaNet-50-500
RetinaNet-101-500
RetinaNet-101-800
YOLOv3-320
YOLOv3-416
YOLOv3-608
mAP
28.0
28.0
29.9
31.2
33.2
36.2
32.5
34.4
37.8
28.2
31.0
33.0
time
61
85
85
125
156
172
73
90
198
22
29
51
Figure 1. We adapt this figure from the Focal Loss paper [9].
YOLOv3 runs significantly faster than other detection methods
with comparable performance. Times from either an M40 or Titan
X, they are basically the same GPU.
2.1. Bounding Box Prediction
Following YOLO9000 our system predicts bounding
boxes using dimension clusters as anchor boxes [15]. The
network predicts 4 coordinates for each bounding box, t
x
,
t
y
, t
w
, t
h
. If the cell is offset from the top left corner of the
image by (c
x
, c
y
) and the bounding box prior has width and
height p
w
, p
h
, then the predictions correspond to:
b
x
= σ(t
x
) + c
x
b
y
= σ(t
y
) + c
y
b
w
= p
w
e
t
w
b
h
= p
h
e
t
h
During training we use sum of squared error loss. If the
ground truth for some coordinate prediction is
ˆ
t
*
our gra-
dient is the ground truth value (computed from the ground
truth box) minus our prediction:
ˆ
t
*
− t
*
. This ground truth
value can be easily computed by inverting the equations
above.
YOLOv3 predicts an objectness score for each bounding
box using logistic regression. This should be 1 if the bound-
ing box prior overlaps a ground truth object by more than
any other bounding box prior. If the bounding box prior
1
arXiv:1804.02767v1 [cs.CV] 8 Apr 2018
下载后可阅读完整内容，剩余5页未读，立即下载
2023-05-26 上传
172 浏览量
2023-03-14 上传
2023-05-09 上传
2023-01-19 上传
2021-08-12 上传
2023-04-23 上传
2019-05-05 上传
2024-02-22 上传
麦滋堡的摸鱼芝士
- 粉丝: 405
- 资源: 10
我的内容管理
展开
最新资源
- 开源通讯录备份系统项目，易于复刻与扩展
- 探索NX二次开发：UF_DRF_ask_id_symbol_geometry函数详解
- Vuex使用教程：详细资料包解析与实践
- 汉印A300蓝牙打印机安卓App开发教程与资源
- kkFileView 4.4.0-beta版：Windows下的解压缩文件预览器
- ChatGPT对战Bard：一场AI的深度测评与比较
- 稳定版MySQL连接Java的驱动包MySQL Connector/J 5.1.38发布
- Zabbix监控系统离线安装包下载指南
- JavaScript Promise代码解析与应用
- 基于JAVA和SQL的离散数学题库管理系统开发与应用
- 竞赛项目申报系统：SpringBoot与Vue.js结合毕业设计
- JAVA+SQL打造离散数学题库管理系统：源代码与文档全览
- C#代码实现装箱与转换的详细解析
- 利用ChatGPT深入了解行业的快速方法论
- C语言链表操作实战解析与代码示例
- 大学生选修选课系统设计与实现：源码及数据库架构
