R-FCN: Object Detection via Region-based Fully Convolutional Networks

May 20, 2016 · Entered Twilight · 🏛 Neural Information Processing Systems

"Last commit was 8.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitattributes, .gitignore, .gitmodules, LICENSE, README.md, data, experiments, external, fetch_data, functions, imdb, models, rfcn_build.m, startup.m, utils

Authors Jifeng Dai, Yi Li, Kaiming He, Jian Sun arXiv ID 1605.06409 Category cs.CV: Computer Vision Citations 6.0K Venue Neural Information Processing Systems Repository https://github.com/daijifeng001/r-fcn ⭐ 1252 Last Checked 1 month ago

Abstract

We present region-based, fully convolutional networks for accurate and efficient object detection. In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image. To achieve this goal, we propose position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection. Our method can thus naturally adopt fully convolutional image classifier backbones, such as the latest Residual Networks (ResNets), for object detection. We show competitive results on the PASCAL VOC datasets (e.g., 83.6% mAP on the 2007 set) with the 101-layer ResNet. Meanwhile, our result is achieved at a test-time speed of 170ms per image, 2.5-20x faster than the Faster R-CNN counterpart. Code is made publicly available at: https://github.com/daijifeng001/r-fcn