# Smoothed Dilated Convolutions for Improved Dense Prediction

arXiv: https://arxiv.org/abs/1808.08931 · HTML: https://mlsanity.com/paper/1808.08931/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 19 of 19)

- [ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models](https://mlsanity.com/paper/2310.07702/) (2023)
- [Aggregated Contextual Transformations for High-Resolution Image Inpainting](https://mlsanity.com/paper/2104.01431/) (2021)
- [Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding](https://mlsanity.com/paper/2104.04386/) (2021)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [Dilated convolution with learnable spacings](https://mlsanity.com/paper/2112.03740/) (2021)
- [Towards Diverse Binary Segmentation via A Simple yet General Gated Network](https://mlsanity.com/paper/2303.10396/) (2023)
- [Understanding the Influence of Receptive Field and Network Complexity in Neural-Network-Guided TEM Image Analysis](https://mlsanity.com/paper/2204.04250/) (2022)
- [Unfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolution](https://mlsanity.com/paper/2308.02794/) (2023)
- [Single Image Dehazing with An Independent Detail-Recovery Network](https://mlsanity.com/paper/2109.10492/) (2021)
- [D2A U-Net: Automatic Segmentation of COVID-19 Lesions from CT Slices with Dilated Convolution and Dual Attention Mechanism](https://mlsanity.com/paper/2102.05210/) (2021)
- [DDCNet: Deep Dilated Convolutional Neural Network for Dense Prediction](https://mlsanity.com/paper/2107.04715/) (2021)
- [A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features](https://mlsanity.com/paper/2105.00967/) (2021)
- [Domain Generalization for Prostate Segmentation in Transrectal Ultrasound Images: A Multi-center Study](https://mlsanity.com/paper/2209.02126/) (2022)
- [Enhancing Satellite Object Localization with Dilated Convolutions and Attention-aided Spatial Pooling](https://mlsanity.com/paper/2505.05599/) (2025)
- [Dense Dilated UNet: Deep Learning for 3D Photoacoustic Tomography Image Reconstruction](https://mlsanity.com/paper/2104.03130/) (2021)
- [Automatic Cell Counting in Flourescent Microscopy Using Deep Learning](https://mlsanity.com/paper/2103.01141/) (2021)
- [CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications](https://mlsanity.com/paper/2104.14126/) (2021)
- [Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation](https://mlsanity.com/paper/2207.09162/) (2022)
- [Supersampling Stable Diffusion and Beyond: A Seamless, Training-Free Approach for Scaling Neural Networks Using Common Interpolation Methods](https://mlsanity.com/paper/2605.08698/) (2026)

## Abstract (arXiv)

Dilated convolutions, also known as atrous convolutions, have been widely explored in deep convolutional neural networks (DCNNs) for various dense prediction tasks. However, dilated convolutions suffer from the gridding artifacts, which hampers the performance. In this work, we propose two simple yet effective degridding methods by studying a decomposition of dilated convolutions. Unlike existing models, which explore solutions by focusing on a block of cascaded dilated convolutional layers, our methods address the gridding artifacts by smoothing the dilated convolution itself. In addition, we point out that the two degridding approaches are intrinsically related and define separable and shared (SS) operations, which generalize the proposed methods. We further explore SS operations in view of operations on graphs and propose the SS output layer, which is able to smooth the entire DCNNs by only replacing the output layer. We evaluate our degridding methods and the SS output layer thoroughly, and visualize the smoothing effect through effective receptive field analysis. Results show that our methods degridding yield consistent improvements on the performance of dense prediction tasks, while adding negligible amounts of extra training parameters. And the SS output layer improves the performance significantly and is very efficient in terms of number of training parameters.