R-CNN论文阅读笔记

Rich feature hierarchies for accurate object detection and semantic segmentation

Ross Girshick

1

Jeff Donahue

1,2

Trevor Darrell

1,2

Jitendra Malik

1

Object detection performance, as measured on the

canonical PASCAL VOC dataset, has plateaued in the last

a mAP of 53.3%. Our approach combines two key insights:

(1) one can apply high-capacity convolutional neural net-

works (CNNs) to bottom-up region proposals in order to

localize and segment objects and (2) when labeled training

data is scarce, supervised pre-training for an auxiliary task,

followed by domain-specific fine-tuning, yields a signifi-

cant performance boost. Since we combine region propos-

als with CNNs, we call our method R-CNN: Regions with

CNN features. We also present experiments that provide

insight into what the network learns, revealing a rich hier-

visual recognition tasks has been based considerably on the

use of SIFT [26] and HOG [7]. But if we look at perfor-

mance on the canonical visual recognition task, PASCAL

VOC object detection [12], it is generally acknowledged

that progress has been slow during 2010-2012, with small

gains obtained by building ensemble systems and employ-

ing minor variants of successful methods.

SIFT and HOG are blockwise orientation histograms,

a representation we could associate roughly with complex

cells in V1, the first cortical area in the primate visual path-

proposals, (3) computes features for each proposal using a large

convolutional neural network (CNN), and then (4) classifies each

region using class-specific linear SVMs. R-CNN achieves a mean

average precision (mAP) of 53.7% on PASCAL VOC 2010. For

comparison, [32] reports 35.1% mAP using the same region pro-

posals, but with a spatial pyramid and bag-of-visual-words ap-

proach. The popular deformable part models perform at 33.4%.

inspired hierarchical and shift-invariant model for pattern

recognition, was an early attempt at just such a process.

The neocognitron, however, lacked a supervised training al-

rise of support vector machines. In 2012, Krizhevsky et al.

[22] rekindled interest in CNNs by showing substantially

higher image classification accuracy on the ImageNet Large

Scale Visual Recognition Challenge (ILSVRC) [9, 10].

Their success resulted from training a large CNN on 1.2

million labeled images, together with a few twists on Le-

Cun’s CNN (e.g., max(x, 0) rectifying non-linearities and

“dropout” regularization).

The significance of the ImageNet result was vigorously

debated during the ILSVRC 2012 workshop. The central