pith. sign in

arxiv: 2104.00742 · v2 · pith:5XMRQTMAnew · submitted 2021-04-01 · 💻 cs.LG · cs.CV

Confidence Calibration for Domain Generalization under Covariate Shift

classification 💻 cs.LG cs.CV
keywords calibrationdomaintargetdomainsadaptationaddressalgorithmscovariate
0
0 comments X
read the original abstract

Existing calibration algorithms address the problem of covariate shift via unsupervised domain adaptation. However, these methods suffer from the following limitations: 1) they require unlabeled data from the target domain, which may not be available at the stage of calibration in real-world applications and 2) their performance depends heavily on the disparity between the distributions of the source and target domains. To address these two limitations, we present novel calibration solutions via domain generalization. Our core idea is to leverage multiple calibration domains to reduce the effective distribution disparity between the target and calibration domains for improved calibration transfer without needing any data from the target domain. We provide theoretical justification and empirical experimental results to demonstrate the effectiveness of our proposed algorithms. Compared against state-of-the-art calibration methods designed for domain adaptation, we observe a decrease of 8.86 percentage points in expected calibration error or, equivalently, an increase of 35 percentage points in improvement ratio for multi-class classification on the Office-Home dataset.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Teaching Models to Express Their Uncertainty in Words

    cs.CL 2022-05 unverdicted novelty 8.0

    GPT-3 can learn to express well-calibrated uncertainty about its answers using natural language phrases rather than logits.