Trident Pyramid Networks: The importance of processing at the feature pyramid level for better object detection

10/08/2021
by   Cédric Picron, et al.
0

Feature pyramids have become ubiquitous in multi-scale computer vision tasks such as object detection. Based on their importance, we divide a computer vision network into three parts: a backbone (generating a feature pyramid), a core (refining the feature pyramid) and a head (generating the final output). Most existing networks operating on feature pyramids, named cores, are shallow and mostly focus on communication-based processing in the form of top-down and bottom-up operations. We present a new core architecture called Trident Pyramid Network (TPN), that allows for a deeper design and for a better balance between communication-based processing and self-processing. We show consistent improvements when using our TPN core on the COCO object detection benchmark, outperforming the popular BiFPN baseline by 1.5 AP. Additionally, we empirically show that it is more beneficial to put additional computation into the TPN core, rather than into the backbone, by outperforming a ResNet-101+FPN baseline with our ResNet-50+TPN network by 1.7 AP, while operating under similar computation budgets. This emphasizes the importance of performing computation at the feature pyramid level in modern-day object detection systems. Code will be released.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/16/2022

Selective Multi-Scale Learning for Object Detection

Pyramidal networks are standard methods for multi-scale object detection...
research
12/11/2019

AugFPN: Improving Multi-scale Feature Learning for Object Detection

Current state-of-the-art detectors typically exploit feature pyramid to ...
research
11/20/2019

EfficientDet: Scalable and Efficient Object Detection

Model efficiency has become increasingly important in computer vision. I...
research
04/07/2020

Feature Pyramid Grids

Feature pyramid networks have been widely adopted in the object detectio...
research
12/02/2019

IPG-Net: Image Pyramid Guidance Network for Object Detection

For Convolutional Neural Network based object detection, there is a typi...
research
05/07/2023

YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification

In this study, we examine the associations between channel features and ...
research
05/20/2021

Content-Augmented Feature Pyramid Network with Light Linear Transformers

Recently, plenty of work has tried to introduce transformers into comput...

Please sign up or login with your details

Forgot password? Click here to reset