DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

06/02/2016
by   Liang-Chieh Chen, et al.
0

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or 'atrous convolution', as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second, we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third, we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed "DeepLab" system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7 results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.

READ FULL TEXT

page 3

page 6

page 8

page 9

page 10

page 11

page 12

page 14

research
12/22/2014

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

Deep Convolutional Neural Networks (DCNNs) have recently shown state of ...
research
06/17/2017

Rethinking Atrous Convolution for Semantic Image Segmentation

In this work, we revisit atrous convolution, a powerful tool to explicit...
research
11/10/2015

Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform

Deep convolutional neural networks (CNNs) are the backbone of state-of-a...
research
11/30/2014

Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection

Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-poo...
research
12/20/2014

A deep-structured fully-connected random field model for structured inference

There has been significant interest in the use of fully-connected graphi...
research
04/18/2021

Gaussian Dynamic Convolution for Efficient Single-Image Segmentation

Interactive single-image segmentation is ubiquitous in the scientific an...
research
03/19/2019

Efficient Smoothing of Dilated Convolutions for Image Segmentation

Dilated Convolutions have been shown to be highly useful for the task of...

Please sign up or login with your details

Forgot password? Click here to reset