ILSVRC2014检测总结

team

results

Spotlights and improve

GoogLeNet

0.439329(6 m)

 0.38(1m)

Rcnn

1. Increase size of super-pixels by 2X

2. Add multibox* proposals

CUHK DeepID-Net

0.406659

RCNN +

Bounding box rejection using def-pooling layer

1000 object-level annotation

200 object-level annotation

Deep Insight

0.404517

Original RCNN                                                                                                                                                                                                                                                       

+ 9conv + SPM

+ more iterations

+ Structural Edge Proposal

+ 7/8/9 Conv Ensemble                                                   

+ CLS Context

NUS

0.37212

Rcnn framework, with nin in cnn

UvA-Euvision

0.354213(aug)

0.32.253(prov)

Selective search + cnn

MSRA Visual Computing

0.351103

 A combination of multiple SPP-net-based models (no outside data)

Berkeley Vision

0.345213

R-CNN baseline