AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Learning to Learn with Variational Information Bottleneck for Domain Generalization

Yingjun Du, Jun Xu, Huan Xiong, Qiang Qiu, Xiantong Zhen, Cees G. M. Snoek, Ling Shao

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 157 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
model classifier parameters as distributions (probabilistic baseline) instead of plain fine-tuned AlexNet (ablation)AlexNet · VLCS (leave-one-domain-out) meanaccuracy: 72.02 -> 73.37Improved
model classifier parameters as distributions (probabilistic baseline) instead of plain fine-tuned AlexNet (ablation)AlexNet · PACS (leave-one-domain-out) meanaccuracy: 69.28 -> 72.63Improved
add regular VIB regularization to probabilistic baseline (ablation)Baseline · VLCS (leave-one-domain-out) meanaccuracy: 73.37 -> 74.01Improved
add regular VIB regularization to probabilistic baseline (ablation)Baseline · PACS (leave-one-domain-out) meanaccuracy: 72.63 -> 73.37Improved
use meta variational information bottleneck instead of regular VIB (ablation)Baseline with VIB · PACS (leave-one-domain-out) meanaccuracy: 73.37 -> 75.74Improved
use meta variational information bottleneck instead of regular VIB (ablation)Baseline with VIB · VLCS (leave-one-domain-out) meanaccuracy: 74.01 -> 74.54Improved
set beta to 0.01 rather than 1 in MetaVIB (ablation)MetaVIB · PACS (leave-one-domain-out) meanaccuracy: 72.02 -> 75.74Improved
set beta to 0.01 rather than 0.001 or 0.1 (ablation)MetaVIB · PACS (leave-one-domain-out) meanaccuracy: 73.89 -> 75.74Improved
set beta to 0.01 rather than 1 on VLCS (ablation)MetaVIB · VLCS (leave-one-domain-out) meanaccuracy: 71.83 -> 74.54Improved
set beta to 0.001 rather than 1 on Rotated MNIST (ablation)MetaVIB · Rotated MNIST (leave-one-angle-out) meanaccuracy: 94.78 -> 97.08Improved
use 10 Monte Carlo samples instead of 1 (ablation)MetaVIB · PACS (leave-one-domain-out) meanaccuracy: 72.93 -> 75.74Improved
increase Monte Carlo samples from 10 to 50 or 100 (ablation)MetaVIB · PACS (leave-one-domain-out) meanaccuracy: 75.74 -> 75.73No clear effect

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