AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Robust Calibration with Multi-domain Temperature Scaling

Yaodong Yu, Stephen Bates, Yi Ma, Michael Jordan

NeurIPS 2022 · Label-efficient and robust learning › Test-time adaptation · approach: Robust optimization for distribution shift · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use multi-domain temperature scaling instead of TSResNet-50 · ImageNet-C InD domainsper-domain ECE (%): 5.80±0.10 -> 3.84±0.05Improved
Use multi-domain temperature scaling instead of TSResNet-50 · ImageNet-C OOD domainsper-domain ECE (%): 5.70±0.06 -> 4.55±0.04Improved
Use multi-domain temperature scaling instead of TSResNet-50 · WILDS-RxRx1 InD domainsper-domain ECE (%): 9.83±0.57 -> 2.85±0.17Improved
Use multi-domain temperature scaling instead of TSResNet-50 · WILDS-RxRx1 OOD domainsper-domain ECE (%): 13.78±0.43 -> 5.25±0.11Improved
Use multi-domain temperature scaling instead of TSResNet-50 · GLDv2 InD domainsper-domain ECE (%): 11.61±0.09 -> 9.90±0.06Improved
Use multi-domain temperature scaling instead of TSResNet-50 · GLDv2 OOD domainsper-domain ECE (%): 10.75±0.14 -> 9.76±0.12Improved
Replace OLS with Ridge regression (ablation)MD-TS with ResNet-50 · WILDS-RxRx1 InD domainsper-domain ECE (%): 2.85 -> 2.88No clear effect
Replace OLS with Ridge regression (ablation)MD-TS with ResNet-50 · WILDS-RxRx1 OOD domainsper-domain ECE (%): 5.25 -> 5.26No clear effect
Replace OLS with Huber regression (ablation)MD-TS with ResNet-50 · WILDS-RxRx1 InD domainsper-domain ECE (%): 2.85 -> 2.90No clear effect
Replace OLS with Huber regression (ablation)MD-TS with ResNet-50 · WILDS-RxRx1 OOD domainsper-domain ECE (%): 5.25 -> 5.29No clear effect
Replace OLS with kernel ridge regression (ablation)MD-TS with ResNet-50 · WILDS-RxRx1 InD domainsper-domain ECE (%): 2.85 -> 2.85No clear effect
Replace OLS with kernel ridge regression (ablation)MD-TS with ResNet-50 · WILDS-RxRx1 OOD domainsper-domain ECE (%): 5.25 -> 4.99Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy