# Learning to Predict Context-adaptive Convolution for Semantic Segmentation

Source: [Learning to Predict Context-adaptive Convolution for Semantic Segmentation](<https://www.sota2.com/research/paper/68fa68311e209131cea1aa48>)

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

Data updated: 2025-10-25T22:31:00.251Z

Authors: Jianbo Liu, Junjun He, Jimmy S. Ren, Yu Qiao, Hongsheng Li

Published: 2020-04-17T13:09:17.000Z

## Abstract

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K.

## 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.

- [Semantic Segmentation on PASCAL Context (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-val.md>): Semantic segmentation; PASCAL Context (val); mIoU: 55.4.

- [Semantic Segmentation on ADE20K (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-val.md>): Semantic segmentation; ADE20K (val); mIoU: 46.12.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2004.08222>)

[PDF](<https://arxiv.org/pdf/2004.08222.pdf>)