Rethink Dilated Convolution for Real-time Semantic Segmentation

11/18/2021
by   Roland Gao, et al.
0

Recent advances in semantic segmentation generally adapt an ImageNet pretrained backbone with a special context module after it to quickly increase the field-of-view. Although successful, the backbone, in which most of the computation lies, does not have a large enough field-of-view to make the best decisions. Some recent advances tackle this problem by rapidly downsampling the resolution in the backbone while also having one or more parallel branches with higher resolutions. We take a different approach by designing a ResNeXt inspired block structure that uses two parallel 3x3 convolutional layers with different dilation rates to increase the field-of-view while also preserving the local details. By repeating this block structure in the backbone, we do not need to append any special context module after it. In addition, we propose a lightweight decoder that restores local information better than common alternatives. To demonstrate the effectiveness of our approach, our model RegSeg achieves state-of-the-art results on real-time Cityscapes and CamVid datasets. Using a T4 GPU with mixed precision, RegSeg achieves 78.3 mIOU on Cityscapes test set at 30 FPS, and 80.9 mIOU on CamVid test set at 70 FPS, both without ImageNet pretraining.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/04/2023

Cross-CBAM: A Lightweight network for Scene Segmentation

Scene parsing is a great challenge for real-time semantic segmentation. ...
research
11/27/2018

ShelfNet for Real-time Semantic Segmentation

In this project, we present ShelfNet, a lightweight convolutional neural...
research
11/02/2019

FDDWNet: A Lightweight Convolutional Neural Network for Real-time Sementic Segmentation

This paper introduces a lightweight convolutional neural network, called...
research
06/24/2019

ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation

The recent years have witnessed great advances for semantic segmentation...
research
05/23/2022

Decoder Denoising Pretraining for Semantic Segmentation

Semantic segmentation labels are expensive and time consuming to acquire...
research
05/22/2020

Bi-direction Context Propagation Network for Real-time Semantic Segmentation

Spatial details and context correlations are two types of critical infor...
research
10/04/2021

A Scalable Factory Backbone for Multiple Independent Time-Sensitive Networks

Convergence of time-sensitive machine control networks as part of the op...

Please sign up or login with your details

Forgot password? Click here to reset