AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Hub-Pathway: Transfer Learning from A Hub of Pre-trained Models

Yang Shu, Zhangjie Cao, Ziyang Zhang, Jianmin Wang, Mingsheng Long

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 1 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
replace learned pathway with random pathway (ablation)Hub-Pathway · COCO-70accuracy: 84.36 -> 80.97Hurt
replace learned pathway with random pathway (ablation)Hub-Pathway · Stanford Carsaccuracy: 91.72 -> 90.61Hurt
remove explore loss (ablation)Hub-Pathway · COCO-70accuracy: 84.36 -> 81.34Hurt
remove explore loss (ablation)Hub-Pathway · Stanford Carsaccuracy: 91.72 -> 89.75Hurt
remove exploit loss (ablation)Hub-Pathway · COCO-70accuracy: 84.36 -> 80.10Hurt
remove exploit loss (ablation)Hub-Pathway · Stanford Carsaccuracy: 91.72 -> 90.59Hurt
data-dependent pathway instead of best single model (ablation)Hub-Pathway · Average (homogeneous hub)accuracy: 83.58 -> 85.63Improved
data-dependent pathway instead of task-level top-2 ensemble (ablation)Hub-Pathway · Average (homogeneous hub)accuracy: 84.31 -> 85.63Improved
per-datum oracle model selection vs learned pathway (ablation)Hub-Pathway · Average (homogeneous hub)accuracy: 85.63 -> 90.48Improved
Hub-Pathway instead of full Ensemble (ablation)Hub-Pathway · CIFAR-100 (homogeneous hub)accuracy: 84.50 -> 85.63Improved
Hub-Pathway instead of ensemble: FLOPs (ablation)Hub-Pathway · CIFAR-100FLOPs (G): 20.55 -> 9.11Improved
Hub-Pathway instead of ensemble: inference speed (ablation)Hub-Pathway · CIFAR-100speed (samples/s): 98.64 -> 240.48Improved

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