AI Paper Atlas

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

Neural Dependencies Emerging From Learning Massive Categories

Ruili Feng, Kecheng Zheng, Kai Zhu, Yujun Shen, Jian Zhao, Yukun Huang, Deli Zhao, Jingren Zhou, Michael Jordan, Zheng-Jun Zha

CVPR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 0 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
Predict unseen categories with a learned linear combination of base-category logitsResNet-50 · ImageNet-1k, 900→100accuracy: 68.47 -> 68.03Hurt
Predict unseen categories with a learned linear combination of base-category logitsResNet-50 · ImageNet-1k, 950→50accuracy: 68.47 -> 68.45No clear effect
Predict unseen categories with a learned linear combination of base-category logitsResNet-50 · ImageNet-1k, 999→1accuracy: 68.47 -> 68.46No clear effect
Predict unseen categories with a learned linear combination of base-category logitsResNet-50 · ImageNet-1k, 999→1 (pos&neg)accuracy: 60.70 -> 61.50Improved
Predict unseen categories with a learned linear combination of base-category logitsSwin-T · ImageNet-1k, 900→100accuracy: 71.49 -> 71.486No clear effect
Predict unseen categories with a learned linear combination of base-category logitsSwin-T · ImageNet-1k, 950→50accuracy: 71.49 -> 71.578No clear effect
Predict unseen categories with a learned linear combination of base-category logitsSwin-T · ImageNet-1k, 999→1accuracy: 71.49 -> 71.56No clear effect
Predict unseen categories with a learned linear combination of base-category logitsSwin-T · ImageNet-1k, 999→1 (pos&neg)accuracy: 76.20 -> 78.00Improved
Add a covariance regularizer to suppress a selected neural dependencyResNet-18 · ImageNet-1kaccuracy: 69.83 -> 70.12Improved
Add a covariance regularizer to suppress a selected neural dependencyResNet-50 · ImageNet-1kaccuracy: 76.37 -> 76.66Improved
Add a covariance regularizer to suppress a selected neural dependencyViT-S · ImageNet-1kaccuracy: 80.67 -> 81.52Improved
Add a covariance regularizer to suppress a selected neural dependencySwin-T · ImageNet-1kaccuracy: 82.16 -> 82.18No 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