# Partial Convolution based Padding

arXiv: https://arxiv.org/abs/1811.11718 · HTML: https://mlsanity.com/paper/1811.11718/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 29 of 29)

- [CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding](https://mlsanity.com/paper/2304.09670/) (2023)
- [MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers](https://mlsanity.com/paper/2205.13137/) (2022)
- [MarioNette: Self-Supervised Sprite Learning](https://mlsanity.com/paper/2104.14553/) (2021)
- [Recurrent Variational Network: A Deep Learning Inverse Problem Solver applied to the task of Accelerated MRI Reconstruction](https://mlsanity.com/paper/2111.09639/) (2021)
- [SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation](https://mlsanity.com/paper/2104.10325/) (2021)
- [Position, Padding and Predictions: A Deeper Look at Position Information in CNNs](https://mlsanity.com/paper/2101.12322/) (2021)
- [Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamics](https://mlsanity.com/paper/2106.11160/) (2021)
- [Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs](https://mlsanity.com/paper/2108.07884/) (2021)
- [Continual 3D Convolutional Neural Networks for Real-time Processing of Videos](https://mlsanity.com/paper/2106.00050/) (2021)
- [DROID: Driver-centric Risk Object Identification](https://mlsanity.com/paper/2106.13201/) (2021)
- [Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility](https://mlsanity.com/paper/2108.08378/) (2021)
- [Repopulating Street Scenes](https://mlsanity.com/paper/2103.16183/) (2021)
- [Padding Module: Learning the Padding in Deep Neural Networks](https://mlsanity.com/paper/2301.04608/) (2023)
- [3D StreetUnveiler with Semantic-aware 2DGS -- a simple baseline](https://mlsanity.com/paper/2405.18416/) (2024)
- [Context-aware Padding for Semantic Segmentation](https://mlsanity.com/paper/2109.07854/) (2021)
- [DRAGON: Decentralized Fault Tolerance in Edge Federations](https://mlsanity.com/paper/2208.07658/) (2022)
- [CASAPose: Class-Adaptive and Semantic-Aware Multi-Object Pose Estimation](https://mlsanity.com/paper/2210.05318/) (2022)
- [Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Framework](https://mlsanity.com/paper/2405.05853/) (2024)
- [Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks](https://mlsanity.com/paper/2108.06925/) (2021)
- [EDeNN: Event Decay Neural Networks for low latency vision](https://mlsanity.com/paper/2209.04362/) (2022)
- [Random Padding Data Augmentation](https://mlsanity.com/paper/2302.08682/) (2023)
- [Imperceptible Adversarial Attack on Deep Neural Networks from Image Boundary](https://mlsanity.com/paper/2308.15344/) (2023)
- [Padding-free Convolution based on Preservation of Differential Characteristics of Kernels](https://mlsanity.com/paper/2309.06370/) (2023)
- [On Symmetries in Convolutional Weights](https://mlsanity.com/paper/2503.19215/) (2025)
- [DRoPS: Dynamic 3D Reconstruction of Pre-Scanned Objects](https://mlsanity.com/paper/2603.24770/) (2026)
- [Single Image Super-Resolution Based on Capsule Neural Networks](https://mlsanity.com/paper/2210.03743/) (2022)
- [Reference Guided Image Inpainting using Facial Attributes](https://mlsanity.com/paper/2301.08044/) (2023)
- [Improving Translation Invariance in Convolutional Neural Networks with Peripheral Prediction Padding](https://mlsanity.com/paper/2307.07725/) (2023)
- [Adversarial Detection with a Dynamically Stable System](https://mlsanity.com/paper/2411.06666/) (2024)

## Abstract (arXiv)

In this paper, we present a simple yet effective padding scheme that can be used as a drop-in module for existing convolutional neural networks. We call it partial convolution based padding, with the intuition that the padded region can be treated as holes and the original input as non-holes. Specifically, during the convolution operation, the convolution results are re-weighted near image borders based on the ratios between the padded area and the convolution sliding window area. Extensive experiments with various deep network models on ImageNet classification and semantic segmentation demonstrate that the proposed padding scheme consistently outperforms standard zero padding with better accuracy.