The code that was used for training is in the ilsvrc branch (still needs some cleanup before merging into master).This model is available in the model package (see below).For more details see the updated R-CNN tech report (Sections 2.5 and 4, in particular).ImageNet 200-class detection results Method These models are available in the model package (see below).VOC 2012 per-class results are available on the VOC 2012 leaderboard.VOC 2010 per-class results are available on the VOC 2010 leaderboard.VOC 2007 per-class results are available in our CVPR14 paper.R-CNN is released under the Simplified BSD License (refer to the If you find R-CNN useful in your research, please consider = , R-CNN was initially described in an arXiv tech report and will appear in a forthcoming CVPR 2014 paper. Unlike the previous best results, R-CNN achieves this performance without using contextual rescoring or an ensemble of feature types. At the time of its release, R-CNN improved the previous best detection performance on PASCAL VOC 2012 by 30% relative, going from 40.9% to 53.3% mean average precision. R-CNN is a state-of-the-art visual object detection system that combines bottom-up region proposals with rich features computed by a convolutional neural network. R-CNN: Region-based Convolutional Neural NetworksĬreated by Ross Girshick, Jeff Donahue, Trevor Darrell and Jitendra Malik at UC Berkeley EECS.Īcknowledgements: a huge thanks to Yangqing Jia for creating Caffe and the BVLC team, with a special shoutout to Evan Shelhamer, for maintaining Caffe and helping to merge the R-CNN fine-tuning code into Caffe. For more recent work that's faster and more accurrate, please see Fast and Faster R-CNN. This code base is no longer maintained and exists as a historical artifact to supplement our CVPR and PAMI papers on Region-based Convolutional Neural Netwoks.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |