mlsanityData to 14 Oct 2026

Context-aware Padding for Semantic Segmentation

arXiv 2109.07854 ↗First posted 16 Sep 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Zero padding is widely used in convolutional neural networks to prevent the size of feature maps diminishing too fast. However, it has been claimed to disturb the statistics at the border. As an alternative, we propose a context-aware (CA) padding approach to extend the image. We reformulate the padding problem as an image extrapolation problem and illustrate the effects on the semantic segmentation task. Using context-aware padding, the ResNet-based segmentation model achieves higher mean Intersection-Over-Union than the traditional zero padding on the Cityscapes and the dataset of DeepGlobe satellite imaging challenge. Furthermore, our padding does not bring noticeable overhead during training and testing.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 31 of its 37 references that are in the map. First posted on arXiv 16 Sep 2021.

Builds on

31 of 37 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2017Squeeze-and-Excitation Networkscited by 4,789
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  9. 2016Pyramid Scene Parsing Networkcited by 2,479
  10. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  11. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  12. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
19 more
  1. 2016Pixel Recurrent Neural Networkscited by 816
  2. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  3. 2018Context Encoding for Semantic Segmentationcited by 290
  4. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 277
  5. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  6. 2017Video Frame Synthesis using Deep Voxel Flowcited by 209
  7. 2015ParseNet: Looking Wider to See Bettercited by 177
  8. 2015Attention to Scale: Scale-aware Semantic Image Segmentationcited by 169
  9. 2018OCNet: Object Context Network for Scene Parsingcited by 140
  10. 2017A Review on Deep Learning Techniques Applied to Semantic Segmentationcited by 122
  11. 2016Learning to Refine Object Segmentscited by 67
  12. 2019Boundless: Generative Adversarial Networks for Image Extensioncited by 62
  13. 2019Very Long Natural Scenery Image Prediction by Outpaintingcited by 50
  14. 2020Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Studycited by 33
  15. 2018Partial Convolution based Paddingcited by 29
  16. 2017Im2Pano3D: Extrapolating 360 Structure and Semantics Beyond the Field of Viewcited by 25
  17. 2018Omnidirectional CNN for Visual Place Recognition and Navigationcited by 22
  18. 2019Convolution with even-sized kernels and symmetric paddingcited by 14
  19. 2018Deep Portrait Image Completion and Extrapolationcited by 12

Built on by

Cited by year

Citing papers per year: 2023: 3.

3 papers.

  1. 2023Padding-free Convolution based on Preservation of Differential Characteristics of Kernelscited by 1
  2. 2023Improving Translation Invariance in Convolutional Neural Networks with Peripheral Prediction Paddingcited by 0
  3. 2023Padding Aware Neuronscited by 0