ME R-CNN: Multi-Expert R-CNN for Object Detection

Abstract

We introduce Multi-Expert Region-based Convolutional Neural Network (ME R-CNN) which is equipped with multiple experts (ME) where each expert is learned to process a certain type of regions of interest (RoIs). This architecture better captures the appearance variations of the RoIs caused by different shapes, poses, and viewing angles. In order to direct each RoI to the appropriate expert, we devise a novel "learnable" network, which we call, expert assignment network (EAN). EAN automatically learns the optimal RoI-expert relationship even without any supervision of expert assignment. As the major components of ME R-CNN, ME and EAN, are mutually affecting each other while tied to a shared network, neither an alternating nor a naive end-to-end optimization is likely to fail. To address this problem, we introduce a practical training strategy which is tailored to optimize ME, EAN, and the shared network in an end-to-end fashion. We show that both of the architectures provide considerable performance increase over the baselines on PASCAL VOC 07, 12, and MS COCO datasets.

IEEE Transactions on Image Processing

References in corpus (6)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Going Deeper with Convolutions
• How good are detection proposals, really?
• Enhanced Object Detection via Fusion With Prior Beliefs from Image Classification
• IOD-CNN: Integrating Object Detection Networks for Event Recognition

Cited by in corpus (4)

• CenterNet: Keypoint Triplets for Object Detection
• Circle Representation for Medical Object Detection
• Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach
• Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection