# Convolutional Random Walk Networks for Semantic Image Segmentation

arXiv: https://arxiv.org/abs/1605.07681 · HTML: https://mlsanity.com/paper/1605.07681/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2016.

## Built on by (most cited first, 20 of 20)

- [ReSTR: Convolution-free Referring Image Segmentation Using Transformers](https://mlsanity.com/paper/2203.16768/) (2022)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [Active Boundary Loss for Semantic Segmentation](https://mlsanity.com/paper/2102.02696/) (2021)
- [Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk](https://mlsanity.com/paper/2105.08248/) (2021)
- [Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation](https://mlsanity.com/paper/2203.02925/) (2022)
- [Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspace](https://mlsanity.com/paper/2102.09896/) (2021)
- [Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification](https://mlsanity.com/paper/2104.13298/) (2021)
- [Graph Reasoning Transformer for Image Parsing](https://mlsanity.com/paper/2209.09545/) (2022)
- [Representing Videos as Discriminative Sub-graphs for Action Recognition](https://mlsanity.com/paper/2201.04027/) (2022)
- [Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary](https://mlsanity.com/paper/2110.01519/) (2021)
- [PLGAN: Generative Adversarial Networks for Power-Line Segmentation in Aerial Images](https://mlsanity.com/paper/2204.07243/) (2022)
- [Local Propagation for Few-Shot Learning](https://mlsanity.com/paper/2101.01480/) (2021)
- [BoundarySqueeze: Image Segmentation as Boundary Squeezing](https://mlsanity.com/paper/2105.11668/) (2021)
- [PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions](https://mlsanity.com/paper/2307.14070/) (2023)
- [Boosting Weakly-Supervised Image Segmentation via Representation, Transform, and Compensator](https://mlsanity.com/paper/2309.00871/) (2023)
- [Proposal-free Lidar Panoptic Segmentation with Pillar-level Affinity](https://mlsanity.com/paper/2204.08744/) (2022)
- [Framework-agnostic Semantically-aware Global Reasoning for Segmentation](https://mlsanity.com/paper/2212.03338/) (2022)
- [CBRW: A Novel Approach for Cancelable Biometric Template Generation based on](https://mlsanity.com/paper/2404.16739/) (2024)
- [A Gift from the Integration of Discriminative and Diffusion-based Generative Learning: Boundary Refinement Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2507.01573/) (2025)
- [Scoliosis Detection using Deep Neural Network](https://mlsanity.com/paper/2210.17269/) (2022)

## Abstract (arXiv)

Most current semantic segmentation methods rely on fully convolutional networks (FCNs). However, their use of large receptive fields and many pooling layers cause low spatial resolution inside the deep layers. This leads to predictions with poor localization around the boundaries. Prior work has attempted to address this issue by post-processing predictions with CRFs or MRFs. But such models often fail to capture semantic relationships between objects, which causes spatially disjoint predictions. To overcome these problems, recent methods integrated CRFs or MRFs into an FCN framework. The downside of these new models is that they have much higher complexity than traditional FCNs, which renders training and testing more challenging. In this work we introduce a simple, yet effective Convolutional Random Walk Network (RWN) that addresses the issues of poor boundary localization and spatially fragmented predictions with very little increase in model complexity. Our proposed RWN jointly optimizes the objectives of pixelwise affinity and semantic segmentation. It combines these two objectives via a novel random walk layer that enforces consistent spatial grouping in the deep layers of the network. Our RWN is implemented using standard convolution and matrix multiplication. This allows an easy integration into existing FCN frameworks and it enables end-to-end training of the whole network via standard back-propagation. Our implementation of RWN requires just 131 additional parameters compared to the traditional FCNs, and yet it consistently produces an improvement over the FCNs on semantic segmentation and scene labeling.