An Implementation of Faster RCNN with Study for Region Sampling
Preprint
Abstract
We adapted the join-training scheme of Faster RCNN framework from Caffe to TensorFlow as a baseline implementation for object detection. Our code is made publicly available. This report documents the simplifications made to the original pipeline, with justifications from ablation analysis on both PASCAL VOC 2007 and COCO 2014. We further investigated the role of non-maximal suppression (NMS) in selecting regions-of-interest (RoIs) for region classification, and found that a biased sampling toward small regions helps performance and can achieve on-par mAP to NMS-based sampling when converged sufficiently.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Training Region-Based Object Detectors with Online Hard Example Mining2016
- Microsoft COCO: Common Objects in Context2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009