# Convolutional CRFs for Semantic Segmentation

arXiv: https://arxiv.org/abs/1805.04777 · HTML: https://mlsanity.com/paper/1805.04777/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2018.

## Built on by (most cited first, 18 of 18)

- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Semantic Diffusion Network for Semantic Segmentation](https://mlsanity.com/paper/2302.02057/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Fully Transformer Networks for Semantic Image Segmentation](https://mlsanity.com/paper/2106.04108/) (2021)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [FSNet: A Failure Detection Framework for Semantic Segmentation](https://mlsanity.com/paper/2108.08748/) (2021)
- [Light-weight Document Image Cleanup using Perceptual Loss](https://mlsanity.com/paper/2105.09076/) (2021)
- [Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction](https://mlsanity.com/paper/2111.15119/) (2021)
- [Transformer-Unet: Raw Image Processing with Unet](https://mlsanity.com/paper/2109.08417/) (2021)
- [Self-Supervised Leaf Segmentation under Complex Lighting Conditions](https://mlsanity.com/paper/2203.15943/) (2022)
- [The Power of One: A Single Example is All it Takes for Segmentation in VLMs](https://mlsanity.com/paper/2503.10779/) (2025)
- [Semantic Segmentation by Improved Generative Adversarial Networks](https://mlsanity.com/paper/2104.09917/) (2021)
- [Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower Species](https://mlsanity.com/paper/2209.04618/) (2022)
- [Towards Integrating Epistemic Uncertainty Estimation into the Radiotherapy Workflow](https://mlsanity.com/paper/2409.18628/) (2024)
- [Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke](https://mlsanity.com/paper/2109.01887/) (2021)
- [Dilated Continuous Random Field for Semantic Segmentation](https://mlsanity.com/paper/2202.00162/) (2022)
- [Optimized Vessel Segmentation: A Structure-Agnostic Approach with Small Vessel Enhancement and Morphological Correction](https://mlsanity.com/paper/2411.15251/) (2024)
- [UnfoldCRF: Structured Mask Refinement with Image-Conditioned Latent Regions](https://mlsanity.com/paper/2609.33996/) (2026)

## Abstract (arXiv)

For the challenging semantic image segmentation task the most efficient models have traditionally combined the structured modelling capabilities of Conditional Random Fields (CRFs) with the feature extraction power of CNNs. In more recent works however, CRF post-processing has fallen out of favour. We argue that this is mainly due to the slow training and inference speeds of CRFs, as well as the difficulty of learning the internal CRF parameters. To overcome both issues we propose to add the assumption of conditional independence to the framework of fully-connected CRFs. This allows us to reformulate the inference in terms of convolutions, which can be implemented highly efficiently on GPUs. Doing so speeds up inference and training by a factor of more then 100. All parameters of the convolutional CRFs can easily be optimized using backpropagation. To facilitating further CRF research we make our implementation publicly available. Please visit: https://github.com/MarvinTeichmann/ConvCRF