DeepAI AI Chat
Log In Sign Up

Efficient Scale-Permuted Backbone with Learned Resource Distribution

10/22/2020
by   Xianzhi Du, et al.
2

Recently, SpineNet has demonstrated promising results on object detection and image classification over ResNet model. However, it is unclear if the improvement adds up when combining scale-permuted backbone with advanced efficient operations and compound scaling. Furthermore, SpineNet is built with a uniform resource distribution over operations. While this strategy seems to be prevalent for scale-decreased models, it may not be an optimal design for scale-permuted models. In this work, we propose a simple technique to combine efficient operations and compound scaling with a previously learned scale-permuted architecture. We demonstrate the efficiency of scale-permuted model can be further improved by learning a resource distribution over the entire network. The resulting efficient scale-permuted models outperform state-of-the-art EfficientNet-based models on object detection and achieve competitive performance on image classification and semantic segmentation. Code and models will be open-sourced soon.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/17/2018

DetNet: A Backbone network for Object Detection

Recent CNN based object detectors, no matter one-stage methods like YOLO...
04/19/2020

ResNeSt: Split-Attention Networks

While image classification models have recently continued to advance, mo...
06/08/2019

DiCENet: Dimension-wise Convolutions for Efficient Networks

In this paper, we propose a new CNN model DiCENet, that is built using: ...
12/10/2019

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

Convolutional neural networks typically encode an input image into a ser...
12/13/2018

ELASTIC: Improving CNNs with Instance Specific Scaling Policies

Scale variation has been a challenge from traditional to modern approach...
06/30/2021

Simple Training Strategies and Model Scaling for Object Detection

The speed-accuracy Pareto curve of object detection systems have advance...
07/29/2018

Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages

Object detection has made great progress in the past few years along wit...