paper-with-me

홈 › Papers

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

2023-12-19 · NeurIPS 2023 11 · Mengyu Wang, Henghui Ding, Jun Hao Liew, Jiajun Liu, Yao Zhao, Yunchao Wei

In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by interpreting segmentation refinement as a data generation process. As a result, the refinement process can be smoothly implemented through a series of denoising diffusion steps. Specifically, SegRefiner takes coarse masks as inputs and refines them using a discrete diffusion process. By predicting the label and corresponding states-transition probabilities for each pixel, SegRefiner progressively refines the noisy masks in a conditional denoising manner. To assess the effectiveness of SegRefiner, we conduct comprehensive experiments on various segmentation tasks, including semantic segmentation, instance segmentation, and dichotomous image segmentation. The results demonstrate the superiority of our SegRefiner from multiple aspects. Firstly, it consistently improves both the segmentation metrics and boundary metrics across different types of coarse masks. Secondly, it outperforms previous model-agnostic refinement methods by a significant margin. Lastly, it exhibits a strong capability to capture extremely fine details when refining high-resolution images. The source code and trained models are available at https://github.com/MengyuWang826/SegRefiner.

📄 PDF Abstract BibTeX arXiv:2312.12425

Code (1)

mengyuwang826/segrefiner 공식 구현 pytorch

Tasks

DenoisingDichotomous Image SegmentationImage SegmentationInstance SegmentationSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

D3RM: A Discrete Denoising Diffusion Refinement Model for Piano Transcription

2025-01-09 · Hounsu Kim, Taegyun Kwon, Juhan Nam

Diffusion models have been widely used in the generative domain due to their convincing performance in modeling complex data distributions. Moreover, they have shown competitive results on discriminative tasks, such as i…

DenoisingImage SegmentationMusic TranscriptionSemantic Segmentation

Towards Agnostic and Holistic Universal Image Segmentation with Bit Diffusion

2026-01-06 · Jakob Lønborg Christensen, Morten Rieger Hannemose, Anders Bjorholm Dahl, Vedrana Andersen Dahl arxiv

This paper introduces a diffusion-based framework for universal image segmentation, making agnostic segmentation possible without depending on mask-based frameworks and instead predicting the full segmentation in a holis…

Image Segmentation

Contour Refinement using Discrete Diffusion in Low Data Regime

2026-02-05 · Fei Yu Guan, Ian Keefe, Sophie Wilkinson, Daniel D. B. Perrakis 외 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 l…

Boundary DetectionImage Segmentation

Bridging Classification and Segmentation in Osteosarcoma Assessment via Foundation and Discrete Diffusion Models

2025-01-03 · Manh Duong Nguyen, Dac Thai Nguyen, Trung Viet Nguyen, Homi Yamada 외

Osteosarcoma, the most common primary bone cancer, often requires accurate necrosis assessment from whole slide images (WSIs) for effective treatment planning and prognosis. However, manual assessments are subjective and…

PrognosisSegmentationwhole slide images

Forward-Free Diffusion Language Models with BPTT-Free Looped Refinement

2026-06-06 · Haotian Sun, Rushi Qiang, Yuqian Zheng, Bo Dai arxiv

Diffusion language models generate text through iterative denoising, offering a powerful alternative to autoregressive generation. However, discrete language spaces lack a natural neighborhood structure for defining effe…