# Context-aware Padding for Semantic Segmentation

Source: [Context-aware Padding for Semantic Segmentation](<https://www.sota2.com/research/paper/68fa6ad41e209131cea2a9b9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:34:16.637Z

Authors: Yu-Hui Huang, Marc Proesmans, Luc Van Gool

Published: 2021-09-16T10:33:21.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.07854>)

[PDF](<https://arxiv.org/pdf/2109.07854.pdf>)