Deep Image: ���Scaling up Image Recognition

Ren Wu Distinguished Scientist, Baidu

wuren@baidu.com @韧在百度

The Color of the Dress

The Color of the Dress

Color Constancy Human vs. Artificial Intelligence

Summary @ GTC14

Big data + Deep learning + High performance computing =

Intelligence

Big data + Deep learning + Heterogeneous computing =

Success

GTC’14: Deep Learning Meets Heterogeneous Computing

Baidu Stock

Baidu Q2’14

Big Data

•  >2000PB Storage •  10-100PB/day Processing •  100b-1000b Webpages •  100b-1000b Index •  1b-10b/day Update •  100TB~1PB/day Log

Computer Chess and Moore’s Law

Deep Blue

A classic example of application-specific system design comprised of an IBM supercomputer with 480 custom-made VLSI chess chips, running massively parallel search algorithm with highly optimized implementation.

Heterogeneous Computing

1993 world #1 Think Machine CM5/1024 131 GFlops

2013 Samsung Note 3 smartphone (Qualcomm SnapDragon 800) 129 Gflops

2000 world #1 ASCI White (IBM RS/6000SP) 6MW power, 106 tons 12.3 TFlops

2013 Two MacPro workstation (dual AMD GPUs each) 14 TFlops

Deep Learning Applications

•  Speech recognition

•  Image recognition

•  Optical character recognition (OCR)

•  Language translation

•  Web search

•  Computational Ads (CTR)

•  …

ImageNet Large-Scale Visual Recognition Challenge

•  ImageNet dataset

•  More than 15 million images belonging to about 22,000 categories

•  ILSVRC (ImageNet Large-Scale Visual Recognition Challenge)

•  Classification task: 1.2 million images contains 1,000 categories

•  One of the most challenging computer vision benchmarks

•  Increasing attention both from industry and academic communities

* Olga Russakovsky et al. ECCV 2014

ImageNet Classification Challenge���

ImageNet classification 2012-2014

Team Year Place Error (top-5) Uses external data

SuperVision 2012 - 16.4% no

SuperVision 2012 1st 15.3% ImageNet 22k

Clarifai 2013 - 11.7% no

Clarifai 2013 1st 11.2% ImageNet 22k

MSRA 2014 3rd 7.35% no

VGG 2014 2nd 7.32% no

GoogLeNet 2014 1st 6.67% no

Slide credit: Yangqing Jia, Google Invincible ?

Our approach – Insights and inspirations

多算胜少算不胜 孙⼦子 (544-496 BC) 计篇 More calculations win, few calculation lose

元元本本殚⻅见洽闻 班固 (32-92 AD) ⻄西都赋 Meaning the more you see the more you know

明⾜足以察秋毫之末 孟⼦子 (372-289 BC) 梁惠⺩王上 ability to see very fine details

Project Minwa – 百度敏娲 •  Minerva + Athena + ⼥女娲 •  Athena: Goddess of Wisdom, Warfare,

Divine Intelligence, Architecture, and Crafts •  Minerva: Goddess of wisdom, magic,

medicine, arts, commerce and defense •  ⼥女娲: 抟⼟土造⼈人, 炼⽯石补天, 婚姻, 乐器

World’s Largest Artificial Neural Networks

v Pushing the State-of-the-Art v ~ 100x bigger than previous ones v New kind of Intelligence?

Hardware/Software Co-design •  Stochastic gradient decent (SGD)

•  High compute density

•  Scale up, up to 100 nodes

•  High bandwidth low latency

•  36 nodes, 144 GPUs, 6.9TB Host, 1.7TB Device

•  0.6 PFLOPS

•  Highly Optimized software stack

•  RDMA/GPU Direct •  New data partition and communication

strategies

GPUs

Infiniband

Minwa

Speedup ( wall time for convergence )

Validation set accuracy for different numbers of GPUs

0  

0.1  

0.2  

0.3  

0.4  

0.5  

0.6  

0.7  

0.8  

0.9  

0.25   0.5   1   2   4   8   16   32   64   128   256  

Acc

ura

cy

Time (hours)

32 GPU 16 GPU 1 GPU

Accuracy 80% 32 GPU: 8.6 hours 1 GPU: 212 hours Speedup: 24.7x

Never have enough training examples! Key observations •  Invariant to illuminant of the

scene •  Invariant to observers

Augmentation approaches •  Color casting •  Optical distortion •  Rotation and cropping etc

Data Augmentation

“⻅见多识⼲⼴广”

And the Color Constancy Key observations •  Invariant to illuminant of the scene •  Invariant to observers

Augmentation approaches •  Color casting •  Optical distortion •  Rotation and cropping etc

The color of the Dress

“Inspired by the color constancy principal. Essentially, this ‘forces’ our neural network to develop its own color constancy ability.”

Data Augmentation

Augmentation The number of possible changes Color casting 68920

Vignetting 1960 Lens distortion 260

Rotation 20 Flipping 2 Cropping 82944(crop size is 224x224, input image

size is 512x512)

Possible variations

The Deep Image system learned from ~2 billion examples, out of 90 billion possible candidates.

Data augmentation vs. Overfitting

Examples

Bathtub Isopod

Indian elephant Ice bear

Some hard cases addressed by adding our data augmentation.

Multi-scale training •  Same crop size, different

resolution

•  Fixed-size 224*224

•  Downsized training images

•  Reduces computational costs

•  But not for state-of-the-art

•  Different models trained by different image sizes

256*256

512*512

•  High-resolution model works

•  256x256: top-5 7.96%

•  512x512: top-5 7.42%

•  Multi-scale models are complementary

•  Fused model: 6.97%

“明查秋毫”

Multi-scale training

Tricycle Washer

Backpack

Little blue heron

Tricycle

Model •  One basic configuration has 16 layers

•  The number of weights in our configuration is 212.7M

•  About 40% bigger than VGG’s

Team Top-1 val. error Top-5 val. error GoogLeNet - 7.89% VGG 25.9% 8.0% Deep Image 24.88% 7.42%

Compare to state-of-the-art

Deep Image has set the new record of 5.98% top-5 error rate for test dataset, a 10.2% relative improvement than the previous best result.

Team Year Place Top-5 test error SuperVision 2012 1 16.42% ISI 2012 2 26.17% VGG 2012 3 26.98% Clarifai 2013 1 11.74% NUS 2013 2 12.95% ZF 2013 3 13.51% GoogLeNet 2014 1 6.66% VGG 2014 2 7.32% MSRA 2014 3 8.06% Andrew Howard 2014 4 8.11% DeeperVision 2014 5 9.51%

Deep Image - - 5.98%

Latest results

Team Date Top-5 test error GoogLeNet 2014 6.66% Deep Image 01/12/2015 5.98% Deep Image 02/05/2015 5.33% Microsoft 02/05/2015 4.94% Google 03/02/2015 4.82% Deep Image 03/17/2015 4.83%

Robustness

Major differentiators •  Customized built supercomputer dedicated for DL

•  Simple, scalable algorithm + Fully optimized software stack

•  Larger models

•  More Aggressive data augmentation

•  Multi-scale, include high-resolution images

Brute force + Insights and push for extreme

Thank you!