mlsanityData to 14 Oct 2026

Partial Convolution based Padding

arXiv 1811.11718 ↗First posted 28 Nov 2018cs.CVcited by 29

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 5; 2023: 7; 2024: 3; 2025: 1; 2026: 1.

29 papers.

Sort:

  1. 2023CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understandingcited by 48
  2. 2022MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformerscited by 47
  3. 2021MarioNette: Self-Supervised Sprite Learningcited by 35
  4. 2021Recurrent Variational Network: A Deep Learning Inverse Problem Solver applied to the task of Accelerated MRI Reconstructioncited by 34
  5. 2021SRWarp: Generalized Image Super-Resolution under Arbitrary Transformationcited by 27
  6. 2021Position, Padding and Predictions: A Deeper Look at Position Information in CNNscited by 26
  7. 2021Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamicscited by 14
  8. 2021Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNscited by 12
  9. 2021Continual 3D Convolutional Neural Networks for Real-time Processing of Videoscited by 9
  10. 2021DROID: Driver-centric Risk Object Identificationcited by 9
  11. 2021Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibilitycited by 8
  12. 2021Repopulating Street Scenescited by 6
17 more
  1. 2023Padding Module: Learning the Padding in Deep Neural Networkscited by 6
  2. 20243D StreetUnveiler with Semantic-aware 2DGS -- a simple baselinecited by 4
  3. 2021Context-aware Padding for Semantic Segmentationcited by 3
  4. 2022DRAGON: Decentralized Fault Tolerance in Edge Federationscited by 2
  5. 2022CASAPose: Class-Adaptive and Semantic-Aware Multi-Object Pose Estimationcited by 2
  6. 2024Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Frameworkcited by 2
  7. 2021Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networkscited by 1
  8. 2022EDeNN: Event Decay Neural Networks for low latency visioncited by 1
  9. 2023Random Padding Data Augmentationcited by 1
  10. 2023Imperceptible Adversarial Attack on Deep Neural Networks from Image Boundarycited by 1
  11. 2023Padding-free Convolution based on Preservation of Differential Characteristics of Kernelscited by 1
  12. 2025On Symmetries in Convolutional Weightscited by 1
  13. 2026DRoPS: Dynamic 3D Reconstruction of Pre-Scanned Objectscited by 1
  14. 2022Single Image Super-Resolution Based on Capsule Neural Networkscited by 0
  15. 2023Reference Guided Image Inpainting using Facial Attributescited by 0
  16. 2023Improving Translation Invariance in Convolutional Neural Networks with Peripheral Prediction Paddingcited by 0
  17. 2024Adversarial Detection with a Dynamically Stable Systemcited by 0