AI Paper Atlas

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

Learning Multiple Tasks with Multilinear Relationship Networks

Mingsheng Long, ZHANGJIE CAO, Jianmin Wang, Philip S Yu

NeurIPS 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 186 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
Add multilinear relationship learning in fc7 as well as fc8 (rather than only fc8) (ablation)MRN · Office-Caltech 5%, 10%, and 20% trainaverage classification accuracy: 92.9 -> 93.8; 93.4 -> 94.5; 94.4 -> 95.5Improved
Add feature and class covariance modeling, not only task covariance (ablation)MRN · Office-Caltech 5%, 10%, and 20% trainaverage classification accuracy: 92.7 -> 93.8; 93.4 -> 94.5; 93.6 -> 95.5Improved
Add multilinear relationship learning in fc7 as well as fc8 (rather than only fc8) (ablation)MRN · Office-Home 5%, 10%, and 20% trainaverage classification accuracy: 56.3 -> 57.0; 62.4 -> 63.0; 66.7 -> 66.9Improved
Add feature and class covariance modeling, not only task covariance (ablation)MRN · Office-Home 5%, 10%, and 20% trainaverage classification accuracy: 55.7 -> 57.0; 62.1 -> 63.0; 66.1 -> 66.9Improved
Add multilinear relationship learning in fc7 as well as fc8 (rather than only fc8) (ablation)MRN · ImageCLEF-DA 5%, 10%, and 20% trainaverage classification accuracy: 67.7 -> 70.3; 71.2 -> 74.3; 73.7 -> 75.3Improved
Add feature and class covariance modeling, not only task covariance (ablation)MRN · ImageCLEF-DA 5%, 10%, and 20% trainaverage classification accuracy: 69.1 -> 70.3; 73.3 -> 74.3; 74.0 -> 75.3Improved
Use tensor-normal multilinear relationships over task-specific layersMRN (full) · Office-Caltech 5%, 10%, and 20% trainaverage classification accuracy: 89.4 -> 93.8; 92.0 -> 94.5; 93.3 -> 95.5Improved
Use tensor-normal multilinear relationships over task-specific layersMRN (full) · Office-Home 5%, 10%, and 20% trainaverage classification accuracy: 53.4 -> 57.0; 60.8 -> 63.0; 66.5 -> 66.9Improved
Use tensor-normal multilinear relationships over task-specific layersMRN (full) · ImageCLEF-DA 5%, 10%, and 20% trainaverage classification accuracy: 62.5 -> 70.3; 69.5 -> 74.3; 72.2 -> 75.3Improved

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