Dilated Residual Networks

Fisher Yu; Vladlen Koltun; Thomas Funkhouser

doi:10.1109/cvpr.2017.75

Abstract

Convolutional networks for image classification progressively reduce resolution until the image is represented by tiny feature maps in which the spatial structure of the scene is no longer discernible. Such loss of spatial acuity can limit image classification accuracy and complicate the transfer of the model to downstream applications that require detailed scene understanding. These problems can be alleviated by dilation, which increases the resolution of output feature maps without reducing the receptive field of individual neurons. We show that dilated residual networks (DRNs) outperform their non-dilated counterparts in image classification without increasing the models depth or complexity. We then study gridding artifacts introduced by dilation, develop an approach to removing these artifacts (degridding), and show that this further increases the performance of DRNs. In addition, we show that the accuracy advantage of DRNs is further magnified in downstream applications such as object localization and semantic segmentation.

Keywords

Dilation (metric space)ResidualArtificial intelligenceComputer scienceSegmentationFeature (linguistics)Pattern recognition (psychology)Computer visionImage segmentationImage resolutionFeature extractionImage (mathematics)Receptive fieldAlgorithmMathematics

Affiliated Institutions

Related Publications

Residual Conv-Deconv Grid Network for Semantic Segmentation

Damien Fourure , Rémi Emonet , Élisa Fromont +3 more

This paper presents GridNet, a new Convolutional Neural Network (CNN)\narchitecture for semantic image segmentation (full scene labelling). Classical\nneural networks are implem...

2017 211 citations

DenseASPP for Semantic Segmentation in Street Scenes

Maoke Yang , Kun Yu , Chi Zhang +2 more

Semantic image segmentation is a basic street scene understanding task in autonomous driving, where each pixel in a high resolution image is categorized into a set of semantic l...

2018 2018 IEEE/CVF Conference on Computer ... 1566 citations

Dual Attention Network for Scene Segmentation

Jun Fu , Jing Liu , Haijie Tian +4 more

In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the self-attention mechanism. Unlike previous works that capture context...

2019 6497 citations

BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation

Changqian Yu , Jingbo Wang , Chao Peng +3 more

Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time ...

2018 Lecture notes in computer science 2572 citations

Scene labeling with LSTM recurrent neural networks

Wonmin Byeon , Thomas M. Breuel , Federico Raue +1 more

This paper addresses the problem of pixel-level segmentation and classification of scene images with an entirely learning-based approach using Long Short Term Memory (LSTM) recu...

2015 401 citations

Publication Info

Year: 2017
Type: article
Citations: 1692
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Dilated Residual Networks

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1692

OpenAlex

Cite This

APA Style

                            
                                    Fisher Yu, 
                                
                                    Vladlen Koltun, 
                                
                                    Thomas Funkhouser
                                
                            (2017). 
                            Dilated Residual Networks. 
                            
                            .
                            https://doi.org/10.1109/cvpr.2017.75

Identifiers

DOI: 10.1109/cvpr.2017.75