Region-Based Convolutional Networks for Accurate Object Detection and Segmentation

• Published in: IEEE transactions on pattern analysis and machine intelligence 2016-01, Vol.38 (1), p.142-158
• Main Authors: Girshick, Ross, Donahue, Jeff, Darrell, Trevor, Malik, Jitendra
• Format: Article
• Language: English
• Subjects: convolutional networks; deep learning; detection; Detectors; Feature extraction; Image segmentation; Object detection; Object recognition; Proposals; semantic segmentation; Support vector machines; Training; transfer learning
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2015.2437384

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 percent relative to the previous best result on VOC 2012-achieving a mAP of 62.4 percent. 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.