Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution

NeurIPS 2019 Thang VuHyunjun JangTrung X. PhamChang D. Yoo

This paper considers an architecture referred to as Cascade Region Proposal Network (Cascade RPN) for improving the region-proposal quality and detection performance by \textit{systematically} addressing the limitation of the conventional RPN that \textit{heuristically defines} the anchors and \textit{aligns} the features to the anchors. First, instead of using multiple anchors with predefined scales and aspect ratios, Cascade RPN relies on a \textit{single anchor} per location and performs multi-stage refinement... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Object Detection COCO test-dev Faster R-CNN (Cascade RPN) box AP 40.6 # 49
AP50 58.9 # 58
AP75 44.5 # 45
APS 22.0 # 55
APM 42.8 # 49
APL 52.6 # 45
Object Detection COCO test-dev Fast R-CNN (Cascade RPN) box AP 40.1 # 54
AP50 59.4 # 53
AP75 43.8 # 50
APS 22.1 # 54
APM 42.4 # 52
APL 51.6 # 49