AI Paper Atlas

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

Importance-aware Co-teaching for Offline Model-based Optimization

Ye Yuan, Can Chen, Zixuan Liu, Willie Neiswanger, Xue Liu

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 0 citations (OpenAlex)

Read the paper

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
add co-teaching (ablation)ICT · TF Bind 8100th percentile normalized ground-truth score: 0.905 ± 0.042 -> 0.958 ± 0.008Improved
add sample reweighting (ablation)ICT · TF Bind 8100th percentile normalized ground-truth score: 0.910 ± 0.024 -> 0.958 ± 0.008Improved
add co-teaching (ablation)ICT · TF Bind 10100th percentile normalized ground-truth score: 0.653 ± 0.018 -> 0.691 ± 0.023Improved
add sample reweighting (ablation)ICT · TF Bind 10100th percentile normalized ground-truth score: 0.654 ± 0.023 -> 0.691 ± 0.023Improved
add co-teaching (ablation)ICT · NAS100th percentile normalized ground-truth score: 0.779 ± 0.071 -> 0.667 ± 0.091Hurt
add sample reweighting (ablation)ICT · NAS100th percentile normalized ground-truth score: 0.666 ± 0.090 -> 0.667 ± 0.091No clear effect
add co-teaching (ablation)ICT · SuperC100th percentile normalized ground-truth score: 0.500 ± 0.017 -> 0.503 ± 0.017No clear effect
add sample reweighting (ablation)ICT · SuperC100th percentile normalized ground-truth score: 0.501 ± 0.017 -> 0.503 ± 0.017No clear effect
add co-teaching (ablation)ICT · Ant Morphology100th percentile normalized ground-truth score: 0.927 ± 0.033 -> 0.961 ± 0.007Improved
add sample reweighting (ablation)ICT · Ant Morphology100th percentile normalized ground-truth score: 0.914 ± 0.015 -> 0.961 ± 0.007Improved
add co-teaching (ablation)ICT · D'Kitty Morphology100th percentile normalized ground-truth score: 0.962 ± 0.021 -> 0.968 ± 0.020No clear effect
add sample reweighting (ablation)ICT · D'Kitty Morphology100th percentile normalized ground-truth score: 0.959 ± 0.013 -> 0.968 ± 0.020No 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