paper-with-me

Papers

A Novel Unsupervised Post-Processing Calibration Method for DNNS with Robustness to Domain Shift

2019-11-25 · Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Christian Gagne

The uncertainty estimation is critical in real-world decision making applications, especially when distributional shift between the training and test data are prevalent. Many calibration methods in the literature have been proposed to improve the predictive uncertainty of DNNs which are generally not well-calibrated. However, none of them is specifically designed to work properly under domain shift condition. In this paper, we propose Unsupervised Temperature Scaling (UTS) as a robust calibration method to domain shift. It exploits unlabeled test samples instead of the training one to adjust the uncertainty prediction of deep models towards the test distribution. UTS utilizes a novel loss function, weighted NLL, which allows unsupervised calibration. We evaluate UTS on a wide range of model-datasets to show the possibility of calibration without labels and demonstrate the robustness of UTS compared to other methods (e.g., TS, MC-dropout, SVI, ensembles) in shifted domains.

📄 PDF Abstract BibTeX arXiv:1911.11195

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Methods 이 논문이 사용한 방법론

Test 설명 없음
TS Spatio-temporal features extraction that measure the stabilty. The proposed method is based on a compression algorithm named Run Length Encoding. The workflow of the method is…

Similar Papers 제목 키워드 기반

Unsupervised Temperature Scaling: Robust Post-processing Calibration for Domain Shift

2019-09-25 · Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Christian Gagne

The uncertainty estimation is critical in real-world decision making applications, especially when distributional shift between the training and test data are prevalent. Many calibration methods in the literature have be…

Decision Making

Uncertainty Quantification for Large-Scale Deep Networks via Post-StoNet Modeling

2025-08-02 · Yan Sun, Faming Liang arxiv

Deep learning has revolutionized modern data science. However, how to accurately quantify the uncertainty of predictions from large-scale deep neural networks (DNNs) remains an unresolved issue. To address this issue, we…

Sparse Learning

Scalable Differential Privacy with Certified Robustness in Adversarial Learning

2020-01-01 · ICML 2020 1 · Hai Phan, My T. Thai, Han Hu, Ruoming Jin 외

In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples. By leveraging the se…

Uncertainty Calibration with Energy Based Instance-wise Scaling in the Wild Dataset

2024-07-17 · Mijoo Kim, Junseok Kwon

With the rapid advancement in the performance of deep neural networks (DNNs), there has been significant interest in deploying and incorporating artificial intelligence (AI) systems into real-world scenarios. However, ma…

Multi-class Classification

Improving Uncertainty Calibration of Deep Neural Networks via Truth Discovery and Geometric Optimization

2021-06-25 · Chunwei Ma, Ziyun Huang, Jiayi Xian, Mingchen Gao 외

Deep Neural Networks (DNNs), despite their tremendous success in recent years, could still cast doubts on their predictions due to the intrinsic uncertainty associated with their learning process. Ensemble techniques and…