# Contour Refinement using Discrete Diffusion in Low Data Regime

arXiv: https://arxiv.org/abs/2602.05880 · HTML: https://mlsanity.com/paper/2602.05880/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 22 of its 47 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [Diffusion Models for Implicit Image Segmentation Ensembles](https://mlsanity.com/paper/2112.03145/) (2021)
- [Ambiguous Medical Image Segmentation using Diffusion Models](https://mlsanity.com/paper/2304.04745/) (2023)
- [Fast Edge Detection Using Structured Forests](https://mlsanity.com/paper/1406.5549/) (2014)
- [RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features](https://mlsanity.com/paper/2104.08569/) (2021)
- [FCN-Transformer Feature Fusion for Polyp Segmentation](https://mlsanity.com/paper/2208.08352/) (2022)
- [Using DUCK-Net for Polyp Image Segmentation](https://mlsanity.com/paper/2311.02239/) (2023)
- [Deep Smoke Segmentation](https://mlsanity.com/paper/1809.00774/) (2018)
- [Object Contour and Edge Detection with RefineContourNet](https://mlsanity.com/paper/1904.13353/) (2019)
- [MaskDiffusion: Exploiting Pre-trained Diffusion Models for Semantic Segmentation](https://mlsanity.com/paper/2403.11194/) (2024)
- [HarDNet-DFUS: An Enhanced Harmonically-Connected Network for Diabetic Foot Ulcer Image Segmentation and Colonoscopy Polyp Segmentation](https://mlsanity.com/paper/2209.07313/) (2022)
- [A Deeply Supervised Semantic Segmentation Method Based on GAN](https://mlsanity.com/paper/2310.04081/) (2023)

## Abstract (arXiv)

Boundary detection of irregular and translucent objects is an important problem with applications in medical imaging, environmental monitoring and manufacturing, where many of these applications are plagued with scarce labeled data and low in situ computational resources. While recent image segmentation studies focus on segmentation mask alignment with ground-truth, the task of boundary detection remains understudied, especially in the low data regime. In this work, we present a lightweight discrete diffusion contour refinement pipeline for robust boundary detection in the low data regime. We use a Convolutional Neural Network(CNN) architecture with self-attention layers as the core of our pipeline, and condition on a segmentation mask, iteratively denoising a sparse contour representation. We introduce multiple novel adaptations for improved low-data efficacy and inference efficiency, including using a simplified diffusion process, a customized model architecture, and minimal post processing to produce a dense, isolated contour given a dataset of size <500 training images. Our method outperforms several SOTA baselines on the medical imaging dataset KVASIR, is competitive on HAM10K and our custom wildfire dataset, Smoke, while improving inference framerate by 3.5X.