AI Paper Atlas

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

Partial-Label and Structure-constrained Deep Coupled Factorization Network

Yan Zhang, Zhao Zhang, Yang Wang, Zheng Zhang, Li Zhang, Shuicheng Yan, Meng Wang

AAAI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 6 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 DS2CF-Net instead of RS2ACFSemi-supervised coupled factorization · USPS digitsAC: 0.7697±0.0690 -> 0.8219±0.0757Improved
Use DS2CF-Net instead of CCFSemi-supervised coupled factorization · USPS digitsF-measure: 0.7461±0.0553 -> 0.7722±0.0708Improved
Use DS2CF-Net instead of SRMCFSemi-supervised coupled factorization · Fashion MNISTAC: 0.7841±0.0460 -> 0.8236±0.0676Improved
Use DS2CF-Net instead of CCFSemi-supervised coupled factorization · Fashion MNISTF-measure: 0.7607±0.0539 -> 0.7991±0.0600Improved
Increase the labeled-sample proportion (ablation)DS2CF-Net · AR, ETH80, USPS, Fashion MNISTClustering accuracyImproved
Increase the number of factorization layers (ablation)DS2CF-Net · AR, ETH80, USPS, Fashion MNISTClustering accuracyImproved

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