AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Learning Deep Disentangled Embeddings With the F-Statistic Loss

Karl Ridgeway, Michael Mozer

NeurIPS 2018 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-grained and cross-domain few-shot baselines · 116 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 the F-statistic loss instead of competing embedding lossesdeep embeddings · CUHK03recall@1 accuracyImproved
Use the F-statistic loss instead of competing embedding lossesdeep embeddings · Market-1501recall@1 accuracyNo clear effect
Use the F-statistic loss instead of competing embedding lossesdeep embeddings · CUB-200-2011recall@1 accuracyHurt
Train with the F-statistic loss rather than triplet or histogram lossSprites representations · SpritesmodularityImproved
Train with the F-statistic loss rather than triplet or histogram lossSmall NORB representations · Small NORBmodularityImproved
Train with the F-statistic loss rather than triplet or histogram lossSmall NORB representations · Small NORBexplicitnessImproved
Train with the F-statistic loss rather than triplet or histogram lossSprites representations · SpritesexplicitnessNo clear effect
Increase β (ablation)β-VAE · SpritesmodularityImproved
Increase β (ablation)β-VAE · SpritesexplicitnessHurt
Replace the F-statistic with the Welch correction for a t statistic (ablation)F-statistic loss · classification datasetsmodel performanceNo clear effect
Use the unnamed-factor oracle rather than unsupervised β-VAE trainingSprites representations · SpritesmodularityImproved
Use the class-aware oracle rather than unsupervised β-VAE trainingSprites representations · SpritesexplicitnessImproved

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