Uncertainty-aware Fine-tuning of Segmentation Foundation Models

Kangning Liu, Brian L. Price, Jason Kuen, Yifei Fan, Zijun Wei +3 more
2/3/2026

No official code found. Best implementation: Kangningthu/SUM (16 stars, last commit 2025-01-09).

Semantic Scholar

Code Implementations(1)

Kangningthu/SUMCommunity63%

Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024).

160PythonSep 25, 20241 years ago
foundation-modelslearning-with-noisy-labelspseudo-labelssegmentation

Similar Papers

Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control

87% match2026

Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization

87% match1 repo202026

BayesTune: Bayesian Sparse Deep Model Fine-tuning

86% match2026

SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation

86% match1 repo1202026

SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning

86% match1 repo262026

LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized Attention

84% match2026

Cite this paper

@article{liu2026uncertaintyaware,
  title  = {Uncertainty-aware Fine-tuning of Segmentation Foundation Models},
  author = {Kangning Liu and Brian L. Price and Jason Kuen and Yifei Fan and Zijun Wei and Luis Figueroa and Krzysztof Geras and C. Fernandez‐Granda},
  year   = {2026},
  url    = {https://www.semanticscholar.org/paper/5e25dc6081924db9403daac2b1b30fffe9dd947f},
  journal = {NEURIPS 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/5e25dc6081924db9403daac2b1b30fffe9dd947f.svg)](https://codeofpaper.com/paper/5e25dc6081924db9403daac2b1b30fffe9dd947f)

Discussion