large scale visual recognition challenge (ilsvrc) 2013: classification spotlights

Post on 14-Jan-2016

214 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

TRANSCRIPT

Large Scale Visual Recognition Challenge (ILSVRC) 2013:

Classification spotlights

Additions to the ConvNet Image Classification PipelineAndrew Howard – Andrew Howard Consulting

Changes to Training:Use more pixels: Train on square patches from rectangular image instead of cropped central squareAdditional color manipulation of contrast, brightness, color balance used on training patches

Changes to Testing:Make Predictions at different scales and different views which use all pixelsPrevious: Used 10 predictions (2 flips * 5 translations)This Submission: Used 90 predictions (2 flips * 5 translations * 3 scales * 3 views)The number of predictions can be reduced with no loss of accuracy with stagewise regression

Higher Resolution Models:Use a fully trained model and fine tune on image patches from a higher resolution imageThis can be trained in about 1/3 the number of epochsPredictions on higher resolution images give complimentary predictions to the base model

Final Vision System achieves 13.6% error and is made of 5 base models and 5 higher resolution modelsStructure is the same as last year with fully connected layers twice as large, which doesn’t add much value

Use Patches From:

Instead of Patches From:

View 1: View 2: View 3:

Cognitive Psychology Inspired Image Classification using Deep Neural Network

Kuiyuan Yang, Microsoft ResearchYalong Bai, Harbin Institute of Technology

Yong Rui, Microsoft Research

CognitiveVision team

Our Classification Scheme

Dog Cat

French bulldog

English setter

Maltese dog

Basic CategoryClassification

Easy to distinguish

DogClassification

Given a image, predict its basic category firstly.

Egyptian cat

Siamese cat

tiger cat

CatClassification

dalmatian

Predict sub category

CognitiveVision team

Caffe: Open-Sourcing Deep LearningYangqing Jia, Trevor Darrell, UC Berkeley

• Convolutional Architecture for Fast Feature Extraction– Seamless switching between CPU and GPU– Fast computation (2.5ms / image with GPU)– Full training and testing capability– Reference ImageNet model available

• A framework to support multiple applications:

Publicly available at http://caffe.berkeleyvision.org/

Classification Embedding Detection Your nextApplication!

Experiments for large scale visual recognition

Deep CNN (following Krizhevsky et al’12)

We tried:+

Low level features &spatial granularities

Where did we fail?

Television (0.18) Hair spray (0.18) Coffee mug (0.10) Flute (0.10)

- TV vs. Screen,

- Coffee mug vs. Cup,

- Flute vs. Microphone,

- …

top 1 acc = 0.567

Appliance and instrument are confusing for us, including

8:30 Classification&localization

10:30 Detection

Noon Discussion panel

14:00 Invited talk by Vittorio Ferrari: Auto-annotation and self-assessment in ImageNet

14:40 Fine-Grained Challenge 2013

Agenda

http://www.image-net.org/challenges/LSVRC/2013/iccv2013

8:50 9:05 9:20 9:35 9:50 Spotlights

10:50 11:10 11:30 11:40Spotlights

top related