# Learning to Predict Context-adaptive Convolution for Semantic Segmentation

arXiv: https://arxiv.org/abs/2004.08222 · HTML: https://mlsanity.com/paper/2004.08222/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2020.

## Built on by (most cited first, 9 of 9)

- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Learning Statistical Texture for Semantic Segmentation](https://mlsanity.com/paper/2103.04133/) (2021)
- [MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking](https://mlsanity.com/paper/2107.10433/) (2021)
- [Learning Local and Global Temporal Contexts for Video Semantic Segmentation](https://mlsanity.com/paper/2204.03330/) (2022)
- [Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes](https://mlsanity.com/paper/2401.15261/) (2024)
- [Cross-attention Spatio-temporal Context Transformer for Semantic Segmentation of Historical Maps](https://mlsanity.com/paper/2310.12616/) (2023)
- [Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation](https://mlsanity.com/paper/2108.01866/) (2021)
- [E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation](https://mlsanity.com/paper/2112.07106/) (2021)
- [Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition](https://mlsanity.com/paper/2110.04042/) (2021)

## Abstract (arXiv)

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.