Dual Path Networks

07/06/2017
by   Yunpeng Chen, et al.
0

In this work, we present a simple, highly efficient and modularized Dual Path Network (DPN) for image classification which presents a new topology of connection paths internally. By revealing the equivalence of the state-of-the-art Residual Network (ResNet) and Densely Convolutional Network (DenseNet) within the HORNN framework, we find that ResNet enables feature re-usage while DenseNet enables new features exploration which are both important for learning good representations. To enjoy the benefits from both path topologies, our proposed Dual Path Network shares common features while maintaining the flexibility to explore new features through dual path architectures. Extensive experiments on three benchmark datasets, ImagNet-1k, Places365 and PASCAL VOC, clearly demonstrate superior performance of the proposed DPN over state-of-the-arts. In particular, on the ImagNet-1k dataset, a shallow DPN surpasses the best ResNeXt-101(64x4d) with 26 size, 25 DPN (DPN-131) further pushes the state-of-the-art single model performance with about 2 times faster training speed. Experiments on the Places365 large-scale scene dataset, PASCAL VOC detection dataset, and PASCAL VOC segmentation dataset also demonstrate its consistently better performance than DenseNet, ResNet and the latest ResNeXt model over various applications.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/25/2016

Resnet in Resnet: Generalizing Residual Architectures

Residual networks (ResNets) have recently achieved state-of-the-art on c...
research
02/06/2018

Mixed Link Networks

Basing on the analysis by revealing the equivalence of modern networks, ...
research
01/25/2018

DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification

In this work, we present a fully automated lung computed tomography (CT)...
research
11/30/2016

Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

The trend towards increasingly deep neural networks has been driven by a...
research
04/30/2019

Object Contour and Edge Detection with RefineContourNet

A ResNet-based multi-path refinement CNN is used for object contour dete...
research
01/03/2021

RegNet: Self-Regulated Network for Image Classification

The ResNet and its variants have achieved remarkable successes in variou...
research
12/31/2021

Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning

Deep convolutional neural networks have been demonstrated to be effectiv...

Please sign up or login with your details

Forgot password? Click here to reset