DeepAI AI Chat
Log In Sign Up

Efficient Scale-Permuted Backbone with Learned Resource Distribution

by   Xianzhi Du, et al.

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.


page 1

page 2

page 3

page 4


DetNet: A Backbone network for Object Detection

Recent CNN based object detectors, no matter one-stage methods like YOLO...

ResNeSt: Split-Attention Networks

While image classification models have recently continued to advance, mo...

DiCENet: Dimension-wise Convolutions for Efficient Networks

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

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

Convolutional neural networks typically encode an input image into a ser...

ELASTIC: Improving CNNs with Instance Specific Scaling Policies

Scale variation has been a challenge from traditional to modern approach...

Simple Training Strategies and Model Scaling for Object Detection

The speed-accuracy Pareto curve of object detection systems have advance...

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

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