# SegFix: Model-Agnostic Boundary Refinement for Segmentation

arXiv: https://arxiv.org/abs/2007.04269 · HTML: https://mlsanity.com/paper/2007.04269/

## Key facts

- Cited by 97 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 30 of 97)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [Reviving Iterative Training with Mask Guidance for Interactive Segmentation](https://mlsanity.com/paper/2102.06583/) (2021)
- [HRFormer: High-Resolution Transformer for Dense Prediction](https://mlsanity.com/paper/2110.09408/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Deep Hierarchical Semantic Segmentation](https://mlsanity.com/paper/2203.14335/) (2022)
- [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://mlsanity.com/paper/2104.02745/) (2021)
- [Mask Transfiner for High-Quality Instance Segmentation](https://mlsanity.com/paper/2111.13673/) (2021)
- [Sparse Instance Activation for Real-Time Instance Segmentation](https://mlsanity.com/paper/2203.12827/) (2022)
- [RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features](https://mlsanity.com/paper/2104.08569/) (2021)
- [Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation](https://mlsanity.com/paper/2104.05239/) (2021)
- [Active Boundary Loss for Semantic Segmentation](https://mlsanity.com/paper/2102.02696/) (2021)
- [PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation](https://mlsanity.com/paper/2101.06175/) (2021)
- [Progressive Semantic Segmentation](https://mlsanity.com/paper/2104.03778/) (2021)
- [Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning](https://mlsanity.com/paper/2210.01035/) (2022)
- [High Quality Segmentation for Ultra High-resolution Images](https://mlsanity.com/paper/2111.14482/) (2021)
- [Semantic Diffusion Network for Semantic Segmentation](https://mlsanity.com/paper/2302.02057/) (2023)
- [AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models](https://mlsanity.com/paper/2404.16233/) (2024)
- [PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation](https://mlsanity.com/paper/2103.06564/) (2021)
- [SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process](https://mlsanity.com/paper/2312.12425/) (2023)
- [Video Mask Transfiner for High-Quality Video Instance Segmentation](https://mlsanity.com/paper/2207.14012/) (2022)
- [Mask Propagation for Efficient Video Semantic Segmentation](https://mlsanity.com/paper/2310.18954/) (2023)
- [Fully Transformer Networks for Semantic Image Segmentation](https://mlsanity.com/paper/2106.04108/) (2021)
- [Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts](https://mlsanity.com/paper/2404.00741/) (2024)
- [SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement](https://mlsanity.com/paper/2502.06756/) (2025)
- [LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning](https://mlsanity.com/paper/2309.13556/) (2023)
- [Guided Patch-Grouping Wavelet Transformer with Spatial Congruence for Ultra-High Resolution Segmentation](https://mlsanity.com/paper/2307.00711/) (2023)

## Abstract (arXiv)

We present a model-agnostic post-processing scheme to improve the boundary quality for the segmentation result that is generated by any existing segmentation model. Motivated by the empirical observation that the label predictions of interior pixels are more reliable, we propose to replace the originally unreliable predictions of boundary pixels by the predictions of interior pixels. Our approach processes only the input image through two steps: (i) localize the boundary pixels and (ii) identify the corresponding interior pixel for each boundary pixel. We build the correspondence by learning a direction away from the boundary pixel to an interior pixel. Our method requires no prior information of the segmentation models and achieves nearly real-time speed. We empirically verify that our SegFix consistently reduces the boundary errors for segmentation results generated from various state-of-the-art models on Cityscapes, ADE20K and GTA5. Code is available at: https://github.com/openseg-group/openseg.pytorch.