Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

NeurIPS 2015 Shaoqing RenKaiming HeRoss GirshickJian Sun

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck... (read more)

PDF Abstract

Code


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Object Detection PASCAL VOC 2007 Faster R-CNN MAP 73.2% # 21
Real-Time Object Detection PASCAL VOC 2007 Faster R-CNN MAP 73.2% # 4
FPS 7 # 5

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Object Counting CARPK Faster R-CNN (2015) MAE 39.88 # 6
RMSE 47.67 # 6
Dense Object Detection SKU-110K Faster-RCNN AP .045 # 5
AP75 .010 # 4