AI Paper Atlas

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

I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively

Haotao Wang, Tianlong Chen, Zhangyang Wang, Kede Ma

ICLR 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 10 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 MAD-selected images to compare models rather than relying only on the fixed ImageNet validation rankingImageNet classifiers · ImageNet validation versus MAD test setSpearman rank-order correlation coefficient: 0.89Mixed
Add squeeze-and-excitation channel-dependency modelingResNet-101 · MAD test setrank: up by two placesImproved
Use progressive cell-wise architecture search instead of global architecture searchNASNet-A-Large · MAD test setrank: 4 -> 7Hurt
Use weakly supervised Instagram hashtag pretrainingWSL-ResNeXt101-32×48 · MAD test setrank: 1 -> 2Improved
Use compound scalingEfficientNet-B7 · MAD test setrank: 2 -> 1Improved
Increase the number of selected images per classifier pair beyond 15 (ablation)MAD · MAD image-classifier rankingSRCC versus top-30 ranking: >0.90Improved

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