HR-RCNN: Hierarchical Relational Reasoning for Object Detection

Abstract

Incorporating relational reasoning in neural networks for object recognition remains an open problem. Although many attempts have been made for relational reasoning, they generally only consider a single type of relationship. For example, pixel relations through self-attention (e.g., non-local networks), scale relations through feature fusion (e.g., feature pyramid networks), or object relations through graph convolutions (e.g., reasoning-RCNN). Little attention has been given to more generalized frameworks that can reason across these relationships. In this paper, we propose a hierarchical relational reasoning framework (HR-RCNN) for object detection, which utilizes a novel graph attention module (GAM). This GAM is a concise module that enables reasoning across heterogeneous nodes by operating on the graph edges directly. Leveraging heterogeneous relationships, our HR-RCNN shows great improvement on COCO dataset, for both object detection and instance segmentation.

To appear at BMVC 2021

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• DSSD : Deconvolutional Single Shot Detector
• High-Resolution Representations for Labeling Pixels and Regions
• Interaction Networks for Learning about Objects, Relations and Physics
• GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
• RON: Reverse Connection with Objectness Prior Networks for Object Detection
• Dive Deeper Into Box for Object Detection