Submission details of TEST_KKANG

Name TEST_KKANG
Paper Link https://arxiv.org/abs/1506.01497
Code Link N/A
AP 0.597179
Input N/A
Runtime 0.038 s
Environment 1 GPU (Titan X)
Abstract 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. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features---using the recently popular terminology of neural networks with attention mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.

Detailed results

Overall precision/recall curve

Per-sequence results

sequence name AP
cubberly-auditorium-2019-04-22_1 0.686425
discovery-walk-2019-02-28_0 0.82107
discovery-walk-2019-02-28_1 0.776177
food-trucks-2019-02-12_0 0.705726
gates-ai-lab-2019-04-17_0 0.721874
gates-basement-elevators-2019-01-17_0 0.828847
gates-foyer-2019-01-17_0 0.805291
gates-to-clark-2019-02-28_0 0.764886
hewlett-class-2019-01-23_0 0.855064
hewlett-class-2019-01-23_1 0.913025
huang-2-2019-01-25_1 0.544261
huang-intersection-2019-01-22_0 0.720659
indoor-coupa-cafe-2019-02-06_0 0.54467
lomita-serra-intersection-2019-01-30_0 0.678122
meyer-green-2019-03-16_1 0.491044
nvidia-aud-2019-01-25_0 0.503495
nvidia-aud-2019-04-18_1 0.756122
nvidia-aud-2019-04-18_2 0.708592
outdoor-coupa-cafe-2019-02-06_0 0.503968
quarry-road-2019-02-28_0 0.673935
serra-street-2019-01-30_0 0.603288
stlc-111-2019-04-19_1 0.805537
stlc-111-2019-04-19_2 0.819135
tressider-2019-03-16_2 0.61979
tressider-2019-04-26_0 0.449797
tressider-2019-04-26_1 0.568503
tressider-2019-04-26_3 0.532633
total 0.597179