AI Paper Atlas

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

Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts

Tao Zhong, Zhixiang Chi, Li Gu, Yang Wang, YUANHAO YU, Jin Tang

NeurIPS 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Mixture and distillation for domain shift · 16 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
mask the in-domain expert during meta-training (ablation)Meta-DMoE · iWildCam OODaccuracy: 74.1 -> 77.2Improved
mask the in-domain expert during meta-training (ablation)Meta-DMoE · iWildCam ID testaccuracy: 76.4 -> 72.9Hurt
increase number of experts from 2 to 10 (ablation)Meta-DMoE · iWildCamaccuracy: 70.4 -> 77.2Improved
meta-learn the aggregator instead of pretraining it (ablation)Meta-DMoE · iWildCamaccuracy: 74.8 -> 77.2Improved
meta-train the student instead of random init (ablation)Meta-DMoE · iWildCamaccuracy: 32.7 -> 77.2Improved
use transformer aggregator instead of average pooling (ablation)Meta-DMoE · iWildCamaccuracy: 69.7 -> 77.2Improved
use transformer aggregator instead of MLP projector (ablation)Meta-DMoE · iWildCamaccuracy: 73.7 -> 77.2Improved
distill features only instead of logits (ablation)Meta-DMoE · iWildCamaccuracy: 72.1 -> 77.2Improved
distill features only instead of logits plus features (ablation)Meta-DMoE · iWildCamaccuracy: 73.1 -> 77.2Improved
increase adaptation images from 2 to 24 (ablation)Meta-DMoE · iWildCamaccuracy: 76.5 -> 77.2Improved
ResNet-50 experts instead of MobileNet V2 experts (ablation)Meta-DMoE · iWildCam (MobileNet V2 student)accuracy / Macro F1: 59.5 -> 58.8 acc; 19.7 -> 21.0 F1Mixed
replace ARM-BN with Meta-DMoEARM-BN · RxRx1accuracy: 31.2 -> 29.8Hurt

Later papers that compared with this method

2 later accepted papers report Meta-DMoE as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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