Jul 16, 2020 · Abstract:Domain Adaptation (DA) enables transferring a learning machine from a labeled source domain to an unlabeled target one.
To tackle this challenge, researchers propose to transfer knowledge from a different but related domain by leveraging the readily-available labeled data, a.k.a. ...
Reviewers agree the paper addressed an important new problem on cross-domain calibration. The motivation is strong, the proposed method is easy to implement ...
In this appendix, we will show more explanations, details, and results that are not included in the main paper. In Preliminaries A, we especially add more ...
Strengths: 1) The paper considers the problem of target prediction calibration in domain adaptation, which is novel to the community; 2) A new Calibration ...
The dilemma that DA models learn higher accuracy at the expense of well-calibrated probabilities is revealed, and Transferable Calibration (TransCal) is ...
In this paper, we delve into the open problem of Calibration in DA, which is extremely challenging due to the coexistence of domain shift and the lack of target ...
Dec 6, 2020 · Driven by this finding, we propose Transferable Calibration (TransCal) to achieve more accurate calibration with lower bias and variance in a ...
Nov 9, 2020 · Domain Adaptation (DA) enables transferring a learning machine from a labeled source domain to an unlabeled target one.
Code release for "Transferable Calibration with Lower Bias and Variance in Domain Adaptation" ... Transferable Calibration with Lower Bias and Variance in Domain ...