AI Paper Atlas

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

Weakly Supervised Collective Feature Learning From Curated Media

Yusuke Mukuta, Akisato Kimura, David Adrian, Zoubin Ghahramani

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 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
Fuse VGG16 with fine-tuned curated-feature representationsVGG16 features · Pinterest, UECFOOD100, UECFOOD256, Apparel, Hipster, InstagramMAP or ACC: 0.430 -> 0.477; 0.511 -> 0.536; 0.468 -> 0.502; 0.576 -> 0.586; 0.592 -> 0.642; 0.910 -> 0.919Improved
Add sparse-coding curated-group features to VGG16VGG16 features · Pinterest, UECFOOD100, UECFOOD256, Apparel, Hipster, InstagramMAP or ACC: 0.430 -> 0.445; 0.511 -> 0.514; 0.468 -> 0.473; 0.576 -> 0.566; 0.592 -> 0.599; 0.910 -> 0.916Mixed
Use sparse-coding curated-group features instead of VGG16 features aloneVGG16 · Pinterest, UECFOOD100, UECFOOD256, Apparel, HipsterMAP or ACC: 0.430 -> 0.409; 0.511 -> 0.454; 0.468 -> 0.376; 0.576 -> 0.488; 0.592 -> 0.552Hurt
Fine-tune VGG16 using curated-group link predictionVGG16 · HipsterACC: 0.592 -> 0.615Improved
Fine-tune VGG16 using curated-group link predictionVGG16 · Pinterest, UECFOOD100, UECFOOD256, Apparel, InstagramMAP or ACC: 0.430 -> 0.404; 0.511 -> 0.453; 0.468 -> 0.398; 0.576 -> 0.470; 0.910 -> 0.896Hurt
Add curated-group latent features to link prediction (ablation)Link prediction model · Small and large link-prediction graphsmean AUC: 0.895 -> 0.928; 0.8442 -> 0.8482Improved
Add image latent features to link prediction (ablation)Link prediction model · Small and large link-prediction graphsmean AUC: 0.895 -> 0.896; 0.8442 -> 0.8460No clear effect
Add both image and curated-group latent features (ablation)Link prediction model · Small and large link-prediction graphsmean AUC: 0.895 -> 0.929; 0.8442 -> 0.8477Improved
Replace the baseline link-prediction model with the proposed model without latent features (ablation)Link prediction model · Small link-prediction graphmean AUC: 0.895 -> 0.898Improved
Replace the baseline link-prediction model with the proposed model without latent features (ablation)Link prediction model · Large link-prediction graphmean AUC: 0.8442 -> 0.8441No 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