Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Deep Learning based object Detection with YOLO v2
Search
Jumabek Alikhanov
September 29, 2019
Research
1
240
Deep Learning based object Detection with YOLO v2
I will briefly go through the the process of YOLOv2
Jumabek Alikhanov
September 29, 2019
Tweet
Share
Other Decks in Research
See All in Research
2025年度人工知能学会全国大会チュートリアル講演「深層基盤モデルの数理」
taiji_suzuki
25
19k
不確実性下における目的と手段の統合的探索に向けた連続腕バンディットの応用 / iot70_gp_rff_mab
monochromegane
2
180
2025/7/5 応用音響研究会招待講演@北海道大学
takuma_okamoto
1
220
「どう育てるか」より「どう働きたいか」〜スクラムマスターの最初の一歩〜
hirakawa51
0
920
機械学習と数理最適化の融合 (MOAI) による革新
mickey_kubo
1
380
snlp2025_prevent_llm_spikes
takase
0
350
情報技術の社会実装に向けた応用と課題:ニュースメディアの事例から / appmech-jsce 2025
upura
0
190
カスタマーサクセスの視点からAWS Summitの展示を考える~製品開発で活用できる勘所~
masakiokuda
2
210
20250605_新交通システム推進議連_熊本都市圏「車1割削減、渋滞半減、公共交通2倍」から考える地方都市交通政策
trafficbrain
0
840
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
0
190
多言語カスタマーインタビューの“壁”を越える~PMと生成AIの共創~ 株式会社ジグザグ 松野 亘
watarumatsuno
0
130
長期・短期メモリを活用したエージェントの個別最適化
isidaitc
0
160
Featured
See All Featured
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
657
61k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
188
55k
What's in a price? How to price your products and services
michaelherold
246
12k
Into the Great Unknown - MozCon
thekraken
40
2.1k
The Straight Up "How To Draw Better" Workshop
denniskardys
237
140k
KATA
mclloyd
32
15k
How to train your dragon (web standard)
notwaldorf
96
6.3k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
132
19k
Context Engineering - Making Every Token Count
addyosmani
5
190
Optimising Largest Contentful Paint
csswizardry
37
3.4k
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
4k
Transcript
Jumabek Alikhanov @Information Security Research Lab, Inha University YOLO9000: Better,
Faster, Stronger (CVPR 2017, Best Paper Honorable Mention) 1
1. Introduction & Previous Work 2. Better detection performance 3.
Faster processing speed 4. Detecting more classes(object types) 5. Conclusion CONTENTS 2
Task & Evaluation Metric mAP- mean Avarage Precision 3 https://github.com/rafaelpadilla/Object-Detection-Metrics
YOLO v1 Network Output shape = (S, S, B×5 +
C) = (7, 7, 2×5 + 20) = (7, 7, 30). 4
YOLOv1: Loss Function pi-conditional class Prob. Ci - box confidence
score 5 Localization Confidence Classification
Previously Pascal 2007 mAP Speed DPM v5 33.7 .07 FPS
14 s/img R-CNN 66.0 .05 FPS 20 s/img Fast R-CNN 70.0 .5 FPS 2 s/img Faster R-CNN 73.2 7 FPS 140 ms/img YOLO 63.4 45 FPS 22 ms/img 6
Previously Pascal 2007 mAP Speed DPM v5 33.7 .07 FPS
14 s/img R-CNN 66.0 .05 FPS 20 s/img Fast R-CNN 70.0 .5 FPS 2 s/img Faster R-CNN 73.2 7 FPS 140 ms/img YOLO 63.4 45 FPS 22 ms/img 7
Better Performance 8
9 YOLO Train on ImageNet Fine-tune on detection Resize network
10 Fine-tune 448x448 Classifier: +3.5% mAP Train on ImageNet Fine-tune
on detection Resize, fine-tune on ImageNet
Anchor boxes use static initialization
Use k-means clustering to find better initializations https://github.com/Jumabek/darknet_scripts
None
Static Anchors vs Dimension Clusters 14
Box Location Prediction 15
Dimension Clusters: +5% mAP
17 Multi-scale training: +1.5% mAP
YOLOv2: Fast, Accurate Detection
Huang, Jonathan, et al. "Speed/accuracy trade-offs for modern convolutional object
detectors." arXiv preprint arXiv:1611.10012 (2016).
Huang, Jonathan, et al. "Speed/accuracy trade-offs for modern convolutional object
detectors." arXiv preprint arXiv:1611.10012 (2016).
Huang, Jonathan, et al. "Speed/accuracy trade-offs for modern convolutional object
detectors." arXiv preprint arXiv:1611.10012 (2016). YOLOv2
None
Faster Detection Speed 23
Speed is not just parameter counts or FLOPs Top 1
Top 5 FLOPs GPU Speed VGG-16 70.5 90.0 30.95 Bn 100 FPS Extraction (YOLOv1) 72.5 90.8 8.52 Bn 180 FPS Resnet50 75.3 92.2 7.66 Bn 90 FPS
Darknet19: A good balance of speed and accuracy Top 1
Top 5 FLOPs GPU Speed VGG-16 70.5 90.0 30.95 Bn 100 FPS Extraction (YOLOv1) 72.5 90.8 8.52 Bn 180 FPS Resnet50 75.3 92.2 7.66 Bn 90 FPS Darknet19 74.0 91.8 5.58 Bn 200 FPS
Why is it fast? Simple & efficient architecture C implementation
26
Stronger - Detecting more classes 27
- 14 million images - 22k classes - Classification labels
- 100k images - 80 classes - Detection labels Golden eagle
Typically use softmax over all classes
Can’t just mash classes together...
Can’t just mash classes together...
WordNet has structure but it’s messy
None
None
... Each node is a conditional probability
... Each node is a conditional probability P(Bedlington terrier) =
P(object) * P (living thing | object) * ….. P(canine | mammal) * P(dog | canine) * P(terrier | dog) * P(Bedlington terrier | terrier)
None
None
None
None
None
None
None
None
None
None
Conclusion • YOLOv2 and YOLO9000 real-time detection systems • YOLOv2
state of the art and faster than other systems • 9K object category detection by YOLO9000 47
1. CVPR paper - https://pjreddie.com/media/files/papers/YOLO9000.pdf 2. Article - https://medium.com/@jonathan_hui/real-time-object-detection-with-yolo-yolov2-28b1b93e2088 3.
Author’s Presentation - https://docs.google.com/presentation/d/14qBAiyhMOFl_wZW4dA1CkixgXwf0zKGbpw_0oHK8yEM/edit#slide=id.g1f9fb98e4b_0 _132 References 48