Region-Based Convolutional Networks for Accurate Object Detection and Segmentation
Title | Region-Based Convolutional Networks for Accurate Object Detection and Segmentation |
Publication Type | Journal Article |
Year of Publication | 2016 |
Authors | Girshick, R., Donahue J., Darrell T., & Malik J. |
Published in | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Volume | 38 |
Issue | 1 |
Page(s) | 142-158 |
Date Published | 01/2016 |
ISSN | 0162-8828 |
Keywords | canonical PASCAL VOC Challenge datasets, convolutional codes, Convolutional Networks, Deep Learning, Detection, Detectors, Feature extraction, high-capacity convolutional networks, image coding, image segmentation, mAP, mean average precision, Object Detection, object recognition, object segmentation, Proposals, region-based convolutional networks, semantic segmentation, source code, source coding, Support vector machines, Training, transfer learning |
Abstract | Object detection performance, as measured on the canonical PASCAL VOC Challenge datasets, plateaued in the final years of the competition. The best-performing methods were complex ensemble systems that typically combined multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 50% relative to the previous best result on VOC 2012achieving a mAP of 62.4%. Our approach combines two ideas: (1) one can apply high-capacity convolutional networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data are scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, boosts performance significantly. Since we combine region proposals with CNNs, we call the resulting model an R-CNN or Region-based Convolutional Network. Source code for the complete system is available at http://www.cs.berkeley.edu/rbg/rcnn. |
URL | http://www.icsi.berkeley.edu/pubs/vision/regionbasedconvolutionalnets16.pdf |
DOI | 10.1109/TPAMI.2015.2437384 |
Abbreviated Authors | R. Girshick, J. Donahue, T. Darrell, and J. Malik |
ICSI Research Group | Vision |
ICSI Publication Type | Article in journal or magazine |