AI Paper Atlas

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

Mining Multi-Label Samples from Single Positive Labels

Youngin Cho, Daejin Kim, Mohammad Azam Khan, Jaegul Choo

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 4 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
apply latent adaptation (method i) to S2M sampling (ablation)S2M sampling · CelebA-ABMNSW B+M+S-A-N-Wsampling iterations to converge: 320 -> 20Improved
apply latent adaptation (method ii, attribute by attribute) (ablation)S2M sampling · CelebA-ABMNSW B+M+S-A-N-Wsampling iterations to converge: 320 -> 15Improved
apply latent adaptation (ii) on class B+M+N+S-A-W (ablation)S2M sampling · CelebA-ABMNSWsampling iterations to converge: 165 -> 5Improved
apply latent adaptation (i) on class B+M+N+S-A-W (ablation)S2M sampling · CelebA-ABMNSWsampling iterations to converge: 165 -> 35Improved
apply latent adaptation (ii) on class A+N+W-B-M-S (ablation)S2M sampling · CelebA-ABMNSWsampling iterations to converge: 335 -> 5Improved
apply latent adaptation (i) on class A+N+W-B-M-S (ablation)S2M sampling · CelebA-ABMNSWsampling iterations to converge: 335 -> 40Improved
apply latent adaptation (ii) on class B+M+S-A-N-W (ablation)S2M sampling · CelebA-ABMNSWaccuracy: 53.51% -> 59.08%Improved
apply latent adaptation (i) on class B+M+N+S-A-W (ablation)S2M sampling · CelebA-ABMNSWaccuracy: 43.78% -> 42.70%No clear effect
apply latent adaptation (ii) on class B+M+S-A-N-W (ablation)S2M sampling · CelebA-ABMNSWFID: 44.72 -> 46.41Hurt
apply latent adaptation (ii) on class B+M+N+S-A-W (ablation)S2M sampling · CelebA-ABMNSWFID: 38.64 -> 37.15Improved
add S2M sampling to unconditional GAN vs second-best methodGAN · MNIST-Evenaccuracy: 87.87 -> 96.37Improved
add S2M sampling to unconditional GAN vs second-best methodGAN · FMNIST-Evenaccuracy: 91.07 -> 97.87Improved

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