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

NeurIPS 2019  ·  Thang Vu, Hyunjun Jang, Trung X. Pham, Chang 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... Each stage is progressively more stringent in defining positive samples by starting out with an anchor-free metric followed by anchor-based metrics in the ensuing stages. Second, to attain alignment between the features and the anchors throughout the stages, \textit{adaptive convolution} is proposed that takes the anchors in addition to the image features as its input and learns the sampled features guided by the anchors. A simple implementation of a two-stage Cascade RPN achieves AR 13.4 points higher than that of the conventional RPN, surpassing any existing region proposal methods. When adopting to Fast R-CNN and Faster R-CNN, Cascade RPN can improve the detection mAP by 3.1 and 3.5 points, respectively. The code is made publicly available at \url{}. read more

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Detection COCO test-dev Fast R-CNN (Cascade RPN) box AP 40.1 # 145
AP50 59.4 # 124
AP75 43.8 # 122
APS 22.1 # 117
APM 42.4 # 126
APL 51.6 # 120
Object Detection COCO test-dev Faster R-CNN (Cascade RPN) box AP 40.6 # 137
AP50 58.9 # 131
AP75 44.5 # 115
APS 22.0 # 121
APM 42.8 # 121
APL 52.6 # 115