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

Abstract

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{https://github.com/thangvubk/Cascade-RPN.git}.

arXiv commentTo appear in NeurIPS 2019 (spotlight)

Cited by in corpus (18)

• Anchor-free Oriented Proposal Generator for Object Detection
• Probabilistic two-stage detection
• Efficient DETR: Improving End-to-End Object Detector with Dense Prior
• PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling
• Ocean: Object-aware Anchor-free Tracking
• Align Deep Features for Oriented Object Detection
• Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN
• Methodology for generating synthetic labeled datasets for visual container inspection
• FC2RN: A Fully Convolutional Corner Refinement Network for Accurate Multi-Oriented Scene Text Detection
• Fast Region Proposal Learning for Object Detection for Robotics
• RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
• Augmenting Proposals by the Detector Itself
• Radar+RGB Attentive Fusion for Robust Object Detection in Autonomous Vehicles
• Semi-Anchored Detector for One-Stage Object Detection
• Disentangle Your Dense Object Detector
• The MIS Check-Dam Dataset for Object Detection and Instance Segmentation Tasks
• Semantic Grouping Network for Video Captioning
• Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing