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
220
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
Vision And Languageモデルにおける異なるドメインでの継続事前学習が性能に与える影響の検証 / YANS2024
sansan_randd
1
110
SSII2025 [SS2] 横浜DeNAベイスターズの躍進を支えたAIプロダクト
ssii
PRO
7
3.6k
【緊急警告】日本の未来設計図 ~沈没か、再生か。国民と断行するラストチャンス~
yuutakasan
0
140
公立高校入試等に対する受入保留アルゴリズム(DA)導入の提言
shunyanoda
0
5.9k
SSII2025 [TS2] リモートセンシング画像処理の最前線
ssii
PRO
7
2.9k
[輪講] SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
nk35jk
2
560
最適決定木を用いた処方的価格最適化
mickey_kubo
4
1.7k
Combinatorial Search with Generators
kei18
0
350
ASSADS:ASMR動画に合わせて撫でられる感覚を提示するシステムの開発と評価 / ec75-shimizu
yumulab
1
400
学生向けアンケート<データサイエンティストについて>
datascientistsociety
PRO
0
3.5k
(NULLCON Goa 2025)Windows Keylogger Detection: Targeting Past and Present Keylogging Techniques
asuna_jp
2
540
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
520
Featured
See All Featured
Building Adaptive Systems
keathley
43
2.7k
Learning to Love Humans: Emotional Interface Design
aarron
273
40k
What's in a price? How to price your products and services
michaelherold
246
12k
Why Our Code Smells
bkeepers
PRO
336
57k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
34
5.9k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
2.9k
Making the Leap to Tech Lead
cromwellryan
134
9.4k
The Straight Up "How To Draw Better" Workshop
denniskardys
234
140k
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
656
60k
KATA
mclloyd
30
14k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
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