GraphFPN: Graph Feature Pyramid Network for Object Detection

08/02/2021
by   Gangming Zhao, et al.
12

Feature pyramids have been proven powerful in image understanding tasks that require multi-scale features. State-of-the-art methods for multi-scale feature learning focus on performing feature interactions across space and scales using neural networks with a fixed topology. In this paper, we propose graph feature pyramid networks that are capable of adapting their topological structures to varying intrinsic image structures and supporting simultaneous feature interactions across all scales. We first define an image-specific superpixel hierarchy for each input image to represent its intrinsic image structures. The graph feature pyramid network inherits its structure from this superpixel hierarchy. Contextual and hierarchical layers are designed to achieve feature interactions within the same scale and across different scales. To make these layers more powerful, we introduce two types of local channel attention for graph neural networks by generalizing global channel attention for convolutional neural networks. The proposed graph feature pyramid network can enhance the multiscale features from a convolutional feature pyramid network. We evaluate our graph feature pyramid network in the object detection task by integrating it into the Faster R-CNN algorithm. The modified algorithm outperforms not only previous state-of-the-art feature pyramid-based methods with a clear margin but also other popular detection methods on both MS-COCO 2017 validation and test datasets.

READ FULL TEXT

page 3

page 4

page 7

research
12/09/2016

Feature Pyramid Networks for Object Detection

Feature pyramids are a basic component in recognition systems for detect...
research
03/27/2018

A Fast Face Detection Method via Convolutional Neural Network

Current face or object detection methods via convolutional neural networ...
research
08/15/2018

SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection

Most of the recent successful methods in accurate object detection build...
research
04/07/2020

Feature Pyramid Grids

Feature pyramid networks have been widely adopted in the object detectio...
research
07/21/2018

Integrating Feature and Image Pyramid: A Lung Nodule Detector Learned in Curriculum Fashion

Lung nodules suffer large variation in size and appearance in CT images....
research
08/24/2018

Deep Feature Pyramid Reconfiguration for Object Detection

State-of-the-art object detectors usually learn multi-scale representati...
research
09/01/2020

SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization

We present a novel framework, Spatial Pyramid Attention Network (SPAN) f...

Please sign up or login with your details

Forgot password? Click here to reset