Dilated Residual Networks

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.

• Publication year

  2017

• Venue

  Computer Vision and Pattern Recognition

• Publication date

  2017-05-28

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/CVPR.2017.75arXiv 1705.09914
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Understanding Convolution for Semantic Segmentation

  2017cited by this paper
• Region-Based Convolutional Networks for Accurate Object Detection and Segmentation

  2016cited by this paper
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

  2016cited by this paper
• The Cityscapes Dataset for Semantic Urban Scene Understanding

  2016cited by this paper
• Learning Deep Features for Discriminative Localization

  2015cited by this paper
• Learning Deconvolution Network for Semantic Segmentation

  2015cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• Multi-Scale Context Aggregation by Dilated Convolutions

  2015influential reference
• Hypercolumns for object segmentation and fine-grained localization

  2014cited by this paper
• Fully convolutional networks for semantic segmentation

  2014influential reference
• ImageNet Large Scale Visual Recognition Challenge

  2014cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014cited by this paper
• Going deeper with convolutions

  2014cited by this paper
• Some Improvements on Deep Convolutional Neural Network Based Image Classification

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Context based object categorization: A critical survey

  2010cited by this paper
• Empirical filter estimation for subpixel interpolation and matching

  2001cited by this paper
• Backpropagation Applied to Handwritten Zip Code Recognition

  1989cited by this paper
• Ieee Transactions on Pattern Analysis and Machine Intelligence 1 80 Million Tiny Images: a Large Dataset for Non-parametric Object and Scene Recognition

  year unknowncited by this paper

• EuleroDec: A Complex-Valued RVQ-VAE for Efficient and Robust Audio Coding

  2026cites this paper
• Semantic–Spatial Feature Refinement Network for Road Extraction From Remote Sensing Images

  2026cites this paper
• S2I-DiT: Unlocking the Semantic-to-Image Transferability by Fine-tuning Large Diffusion Transformer Models

  2026cites this paper
• Dual-task collaborative optimization for fundus image disease diagnosis and quality assessment.

  2026cites this paper
• Uncertainty-aware genomic deep learning with knowledge distillation

  2026cites this paper
• A data-driven decision model for selecting ML models in research software

  2026cites this paper
• DCENet: A Dilated Convolution and Attention-Based Network for LPI Radar Signal Modulation Recognition

  2026cites this paper
• Joint Identification of Encoders and Interleavers Using Deep Learning With Hardware Validation

  2026cites this paper
• A Rotationally Equivariant Attention Framework for Integrated Inshore Ship Detection and Fine-Grained Classification

  2026cites this paper
• POP-YOLOv8: an object detection framework for partially occluded pedestrians in nighttime traffic environments

  2026cites this paper
• Real-time Anomaly Detection in Aviation Composites: An Edge Computing Framework for Acoustic Tap Test

  2026cites this paper
• A lightweight framework with adaptive feature enhancement for accurate pavement distress evaluation

  2026cites this paper
• An Elastic Coding and Decoding Method for Satellite Remote Sensing Image Semantic Transmission

  2026cites this paper
• WADEPre: A Wavelet-based Decomposition Model for Extreme Precipitation Nowcasting with Multi-Scale Learning

  2026cites this paper
• Multimodal fusion via ship trajectory understanding for cognitive maritime intelligence: A case study of the Fujian sea

  2026cites this paper
• DA-TransResUNet: Residual U-Net Liver Segmentation Model Integrating Dual Attention of Spatial and Channel with Transformer

  2026cites this paper
• Structure-Consistent Contrastive Learning for Unpaired Image Translation With Gradient-Domain Constraints

  2026influential citation
• A multi-scale dilated convolutional neural network-based bearing fault diagnosis method with dense connections under strong noise conditions

  2026influential citation
• M3-UNet: Multi-frequency, multi-scale and multi-task U-Net for intima-media complex segmentation

  2026cites this paper
• Online Opinion Trend Prediction for Public Health Events Based on Time Series Transformer

  2026cites this paper
• DDConv: Dynamic Dilated Convolution

  2026cites this paper
• Quantifying freeze damage in strawberry plants using deep learning-based semantic segmentation

  2026cites this paper
• 基于半监督学习的血管内光学相干层析成像血管支架检测方法

  2026cites this paper
• xMHAC-PDCNN: An Explainable Deep Network with Spatial Feature Embedding for Fault Detection and Diagnosis of Chillers Under Variable Operating Conditions

  2025cites this paper
• Evaluating the representational power of pre-trained DNA language models for regulatory genomics

  2025influential citation
• ASC-SW: Atrous strip convolution network with sliding windows for visual-assisted map navigation

  2025cites this paper
• QualityDDH: visualized standardization of neonatal hip ultrasound via a structural prior regression framework

  2025cites this paper
• Actinic defect inspection and characterization for extreme ultraviolet mask blanks

  2025cites this paper
• Pixel Embedding Method for Tubular Neurite Segmentation

  2025cites this paper
• Small Object Detection Based on YOLOv5s in Advanced Driver Assistance System

  2025cites this paper
• MLRU++: Multiscale Lightweight Residual UNETR++ with Attention for Efficient 3D Medical Image Segmentation

  2025cites this paper
• A novel bearing fault diagnosis method using a hybrid TCN-transformer architecture: A deep learning approach

  2025cites this paper
• Spatial Frequency Modulation for Semantic Segmentation

  2025cites this paper
• GLMF-NET: global and local multi-scale fusion network for polyp segmentation

  2025cites this paper
• Deep learning methods for autonomous driving scene understanding tasks: A review

  2025cites this paper
• Dilated Neural Networks for Improving Microaneurysm Detection in Fundus Images

  2025cites this paper
• HLMamba: Hybrid Lightweight Mamba-Based Fusion Network for Dense Prediction of Remote Sensing Images

  2025cites this paper
• Optimizing Residual Networks: Exploring Subblock Variations and Extended Residual Connections in Shallow Architectures

  2025cites this paper
• Lightweight RGB-D Salient Object Detection From a Speed-Accuracy Tradeoff Perspective

  2025cites this paper
• An End-to-End Comprehensive Gear Fault Diagnosis Method Based on Multi-Scale Feature-Level Fusion Strategy

  2025cites this paper
• Comparison of Deep Learning Methods and a Transfer-Learning Semisupervised Generative-Adversarial-Network Combined Framework for Pavement Crack Image Identification

  2025cites this paper
• Multiscale deformed attention networks for white blood cell detection

  2025cites this paper
• 基于密集混合注意力网络的遥感影像建筑物变化检测

  2025cites this paper
• Sliced Wasserstein Discrepancy in Disentangling Representation and Adaptation Networks for Unsupervised Domain Adaptation

  2025cites this paper
• A semi-supervised method using cycle consistency and multi-perspective dilated for SAR-to-optical translation

  2025cites this paper
• High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion

  2025cites this paper
• Combining Self-Attention and Dilation Convolutional for Semantic Segmentation of Coal Maceral Groups

  2025cites this paper
• EAAC-S2S: East Asian Atmospheric Circulation S2S Forecasting with a Deep Learning Model Considering Multi-Sphere Coupling

  2025cites this paper
• MCT-Net: a multi-branch hybrid CNN-transformer model for medical image segmentation

  2025cites this paper
• Weakly supervised free-space segmentation by fusing spatial priors and region features for auto-driving

  2025cites this paper
• A Review of the Long Horizon Forecasting Problem in Time Series Analysis

  2025cites this paper
• Dual cross transformer based on multi-scale fusion for fine-grained action recognition

  2025cites this paper
• Exploring Adapter Design Tradeoffs for Low Resource Music Generation

  2025cites this paper
• TOMD: A Trail-based Off-road Multimodal Dataset for Traversable Pathway Segmentation under Challenging Illumination Conditions

  2025cites this paper
• BWFormer: Building Wireframe Reconstruction from Airborne LiDAR Point Cloud with Transformer

  2025cites this paper
• Noise-Resistant Video Anomaly Detection via RGB Error-Guided Multiscale Predictive Coding and Dynamic Memory

  2025cites this paper
• Multi-scale feature fusion keypoint detection network for ship draft line localization

  2025cites this paper
• Basketball Small Object Detection Algorithm Based on Improved YOLO v7

  2025cites this paper
• Enhanced remote sensing image feature classification using STFF-PSPNet

  2025cites this paper
• Improving Consumer Experience With Pre-Purify Temporal-Decay Memory-Based Collaborative Filtering Recommendation for Graduate School Application

  2025cites this paper
• Dynamic Snake Convolution Neural Network for Enhanced Image Super-Resolution

  2025cites this paper
• Accuracy Assessment for Multibaseline Phase Unwrapping Without Using External Reference Data

  2025cites this paper
• ASP-VMUNet: Atrous Shifted Parallel Vision Mamba U-Net for Skin Lesion Segmentation

  2025influential citation
• Extended multi-scale feature fusion and balanced generative adversarial network for image inpainting under limited data

  2025cites this paper
• Pixel level deep reinforcement learning for accurate and robust medical image segmentation

  2025cites this paper
• SICFNet: Shared Information Interaction and Complementary Feature Fusion Network for RGB-T traffic scene parsing

  2025cites this paper
• Frequency Dynamic Convolution for Dense Image Prediction

  2025cites this paper
• A lightweight approach for accurate detection of pipeline weld defects

  2025cites this paper
• MMUnet: medical image segmentation via multi-branch and multi-scale Unet

  2025cites this paper
• AutoDDH: A dual-attention multi-task network for grading developmental dysplasia of the hip in ultrasound images

  2025influential citation
• Expression recognition method based on feature redundancy optimization

  2025cites this paper
• AFR: An image-aided diagnostic approach for ulcerative colitis

  2025cites this paper
• Small-Object Semantic Segmentation of Satellite Ship Images Using Modified U-Net With Morphological Loss

  2025cites this paper
• A Content-Aware Method for Detecting External-Force-Damage Objects on Transmission Lines

  2025cites this paper
• Hierarchical Heterogeneous Geometric Foreground Perception Network for Remote Sensing Object Detection

  2025cites this paper
• Identification of stochastic gravitational wave backgrounds from cosmic strings using machine learning

  2025cites this paper
• HGFormer: Topology-Aware Vision Transformer With HyperGraph Learning

  2025cites this paper
• SegRet: An Efficient Design for Semantic Segmentation with Retentive Network

  2025cites this paper
• A local generation-mix cascade network for image translation with limited data

  2025cites this paper
• AKDT: Adaptive Kernel Dilation Transformer for Effective Image Denoising

  2025cites this paper
• CrossHash: Cross-scale Vision Transformer Hashing for Image Retrieval

  2025cites this paper
• Secure UAV routing with Gannet Optimization and Shepard Networks

  2025cites this paper
• Precision in Pathology: PMA-DETR Elevates Tumor Lesion Detection

  2025cites this paper
• MSDAHNet: A multi-scale dual attention hybrid convolution network for breast tumor segmentation

  2025cites this paper
• Multi-stage feature aggregation transformer for image rain and haze joint removal

  2025cites this paper
• Sgmsnet: self-guided multi-scale fusion network for remote sensing image scene classification

  2025cites this paper
• vGamba: Attentive State Space Bottleneck for efficient Long-range Dependencies in Visual Recognition

  2025cites this paper
• Center-Symmetry Representation-Based High-Quality Localization Detector for Oriented Object Detection

  2025cites this paper
• COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking

  2025cites this paper
• EMCAH-Net: an effective multi-scale context aggregation hybrid network for medical image segmentation

  2025cites this paper
• Addressing biases in gastric cancer diagnosis through generative models and vision-based surface tactile sensing

  2025cites this paper
• Lw4s: a lightweight semantic sigmentation model of urban street scene

  2025cites this paper
• Recognition of Residual Cores in Aero-Engine Blade Neutron Images Using Improved Patch SVDD

  2025cites this paper
• Skin Lesions Segmentation Method Based on Diffusion Model

  2025cites this paper
• Visual Affordance Prediction: Survey and Reproducibility

  2025cites this paper
• MSFRNet: Multiscale Feature Recomposition Network for SingleImage Dehazing

  2025cites this paper
• Bidirectional graphics-based digital twin framework for quantifying seismic damage of structures using deep learning networks

  2025cites this paper
• Filamentary Convolution for SLI: A Brain-Inspired Approach with High Efficiency

  2025cites this paper
• Semantic Segmentation of Ocular Regions Using Artificial Intelligence for Biometric and Medical Uses

  2025cites this paper
• A Predictive Approach for Enhancing Accuracy in Remote Robotic Surgery Using Informer Model

  2025cites this paper