# Conditional Random Fields as Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1502.03240 · HTML: https://mlsanity.com/paper/1502.03240/

## Key facts

- Cited by 214 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2015.

## Built on by (most cited first, 30 of 214)

- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [A Comprehensive Survey of Scene Graphs: Generation and Application](https://mlsanity.com/paper/2104.01111/) (2021)
- [ReSTR: Convolution-free Referring Image Segmentation Using Transformers](https://mlsanity.com/paper/2203.16768/) (2022)
- [One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation](https://mlsanity.com/paper/2104.02246/) (2021)
- [GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models](https://mlsanity.com/paper/2210.02025/) (2022)
- [Scene Graph Generation: A Comprehensive Survey](https://mlsanity.com/paper/2201.00443/) (2022)
- [Representation Compensation Networks for Continual Semantic Segmentation](https://mlsanity.com/paper/2203.05402/) (2022)
- [CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor](https://mlsanity.com/paper/2312.07661/) (2023)
- [CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision](https://mlsanity.com/paper/2203.01475/) (2022)
- [Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation](https://mlsanity.com/paper/2108.02376/) (2021)
- [GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer](https://mlsanity.com/paper/2108.12630/) (2021)
- [A Survey on Green Deep Learning](https://mlsanity.com/paper/2111.05193/) (2021)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [Mining Contextual Information Beyond Image for Semantic Segmentation](https://mlsanity.com/paper/2108.11819/) (2021)
- [Pseudo-mask Matters in Weakly-supervised Semantic Segmentation](https://mlsanity.com/paper/2108.12995/) (2021)
- [Equivariant Hypergraph Diffusion Neural Operators](https://mlsanity.com/paper/2207.06680/) (2022)
- [SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents](https://mlsanity.com/paper/2601.16746/) (2026)
- [CTNet: Context-based Tandem Network for Semantic Segmentation](https://mlsanity.com/paper/2104.09805/) (2021)
- [Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models](https://mlsanity.com/paper/2309.11420/) (2023)
- [Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization](https://mlsanity.com/paper/2103.13041/) (2021)
- [HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding](https://mlsanity.com/paper/2105.07751/) (2021)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection](https://mlsanity.com/paper/2312.01696/) (2023)
- [NeuPSL: Neural Probabilistic Soft Logic](https://mlsanity.com/paper/2205.14268/) (2022)
- [Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors](https://mlsanity.com/paper/2211.13224/) (2022)
- [SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images](https://mlsanity.com/paper/2101.07422/) (2021)
- [CLUSTSEG: Clustering for Universal Segmentation](https://mlsanity.com/paper/2305.02187/) (2023)

## Abstract (arXiv)

Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To this end, we formulate mean-field approximate inference for the Conditional Random Fields with Gaussian pairwise potentials as Recurrent Neural Networks. This network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a deep network that has desirable properties of both CNNs and CRFs. Importantly, our system fully integrates CRF modelling with CNNs, making it possible to train the whole deep network end-to-end with the usual back-propagation algorithm, avoiding offline post-processing methods for object delineation. We apply the proposed method to the problem of semantic image segmentation, obtaining top results on the challenging Pascal VOC 2012 segmentation benchmark.