Rethinking Atrous Convolution for Semantic Image Segmentation

Published in

arXiv.org(2017)

External Links:

Generate Graph

TL;DR

The proposed `DeepLabv3' system significantly improves over the previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.

Abstract

In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.

Authors

Liang-Chieh Chen

14 papers

Florian Schroff

8 papers

Hartwig Adam

15 papers

References96 items

Ladder-Style DenseNets for Semantic Segmentation of Large Natural Images

Scale-Adaptive Convolutions for Scene Parsing

Deep Dual Learning for Semantic Image Segmentation

Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions

Stacked Deconvolutional Network for Semantic Segmentation

Rethinking Atrous Convolution for Semantic Image Segmentation

Published in

arXiv.org(2017)

External Links:

Generate Graph

TL;DR

Abstract

Authors

Liang-Chieh Chen

14 papers

Florian Schroff

8 papers

Hartwig Adam

15 papers

References96 items

Ladder-Style DenseNets for Semantic Segmentation of Large Natural Images

Scale-Adaptive Convolutions for Scene Parsing

Deep Dual Learning for Semantic Image Segmentation

Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions

Stacked Deconvolutional Network for Semantic Segmentation

G. Papandreou

4 papers

Semantic Video CNNs Through Representation Warping

FoveaNet: Perspective-Aware Urban Scene Parsing

Scene Parsing through ADE20K Dataset

Revisiting Unreasonable Effectiveness of Data in Deep Learning Era

Learning Object Interactions and Descriptions for Semantic Image Segmentation

Gated Feedback Refinement Network for Dense Image Labeling

Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF

Recurrent Scene Parsing with Perspective Understanding in the Loop

Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade

Deformable Convolutional Networks

Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network

Understanding Convolution for Semantic Segmentation

FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos

Beyond Skip Connections: Top-Down Modulation for Object Detection

COCO-Stuff: Thing and Stuff Classes in Context

Feature Pyramid Networks for Object Detection

Pyramid Scene Parsing Network

Video Scene Parsing with Predictive Feature Learning

Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes

Mixed context networks for semantic segmentation

Xception: Deep Learning with Depthwise Separable Convolutions

Multi-Level Contextual RNNs With Attention Model for Scene Labeling

Gaussian Conditional Random Field Network for Semantic Segmentation

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

Wide Residual Networks

Bridging Category-level and Instance-level Semantic Image Segmentation

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Laplacian Reconstruction and Refinement for Semantic Segmentation

The Cityscapes Dataset for Semantic Urban Scene Understanding

Fast, Exact and Multi-scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs

Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Deep Residual Learning for Image Recognition

Multi-Scale Context Aggregation by Dilated Convolutions

Zoom Better to See Clearer: Human Part Segmentation with Auto Zoom Net

Semantic Object Parsing with Local-Global Long Short-Term Memory

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

Attention to Scale: Scale-Aware Semantic Image Segmentation

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Semantic Image Segmentation via Deep Parsing Network

ParseNet: Looking Wider to See Better

Modeling local and global deformations in Deep Learning: Epitomic convolution, Multiple Instance Learning, and sliding window detection

Scene labeling with LSTM recurrent neural networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

Learning Deconvolution Network for Semantic Segmentation

Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation

Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks

Distilling the Knowledge in a Neural Network

Fully Connected Deep Structured Networks

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Conditional Random Fields as Recurrent Neural Networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

Convolutional feature masking for joint object and stuff segmentation

Feedforward semantic segmentation with zoom-out features

Hypercolumns for object segmentation and fine-grained localization

Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture

Fully convolutional networks for semantic segmentation

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet Large Scale Visual Recognition Challenge

The Pascal Visual Object Classes Challenge: A Retrospective

The Role of Context for Object Detection and Semantic Segmentation in the Wild

Recurrent Convolutional Neural Networks for Scene Labeling

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Microsoft COCO: Common Objects in Context

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Learning Hierarchical Features for Scene Labeling

Fast image scanning with deep max-pooling convolutional neural networks

ImageNet classification with deep convolutional neural networks

Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

Adaptive deconvolutional networks for mid and high level feature learning

Semantic contours from inverse detectors

Fast High‐Dimensional Filtering Using the Permutohedral Lattice

Decomposing a scene into geometric and semantically consistent regions

Associative hierarchical CRFs for object class image segmentation

Robust Higher Order Potentials for Enforcing Label Consistency

Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

The pyramid match kernel: discriminative classification with sets of image features

Multiscale conditional random fields for image labeling

Long Short-Term Memory

Backpropagation Applied to Handwritten Zip Code Recognition

Image Analysis Using Multigrid Relaxation Methods

Multi-level adaptive solutions to boundary-value problems math comptr

Multigrid Geometric Active Contour Models

TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context

A real-time algorithm for signal analysis with the help of the wavelet transform

A multigrid tutorial

Field of Study

Computer Science

Journal Information

Name

ArXiv

Volume

abs/2005.00687

Venue Information

Name

arXiv.org

Type

URL

https://arxiv.org

Alternate Names

ArXiv