AI Paper Atlas

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

GANmut: Learning Interpretable Conditional Space for Gamut of Emotions

Stefano d'Apolito, Danda Pani Paudel, Zhiwu Huang, Andres Romero, Luc Van Gool

CVPR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 25 citations (OpenAlex)

Check 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
Learn a Gaussian conditional emotion space rather than conditioning only on basic emotion labelsStarGAN-based emotion generation · Complex emotion reconstruction, Setting 1ERE: 0.038 -> 0.020Improved
Learn a Gaussian conditional emotion space rather than conditioning only on basic emotion labelsStarGAN-based emotion generation · Complex emotion reconstruction, Setting 2ERE: 0.037 -> 0.018Improved
Learn a linear conditional emotion space rather than conditioning only on basic emotion labelsStarGAN-based emotion generation · AffectNet test setFED: 4.89 -> 0.71Improved
Learn a Gaussian conditional emotion space rather than conditioning only on basic emotion labelsStarGAN-based emotion generation · AffectNet test setFED: 4.89 -> 18.32Hurt
Increase the radial-loss weight from λρ=1 to λρ=4 (ablation)GANmut · Neutral-to-basic emotion interpolationsemantic smoothnessImproved
Use a learned continuous conditional space instead of categorical conditioningEmotion generation · Neutral-to-basic emotion interpolationsmoothness scoreImproved

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