AI Paper Atlas

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

f-Similarity Preservation Loss for Soft Labels: A Demonstration on Cross-Corpus Speech Emotion Recognition

Biqiao Zhang, Yuqing Kong, Georg Essl, Emily Mower Provost

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 14 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
add f-SPL (KL) multi-task loss to cross-entropyConv-Pool SER · MSP->IEMOCAP ValenceUAR (%): 64.45 -> 66.01Improved
add f-SPL (KL) lossConv-Pool SER · MSP->IEMOCAP ActivationUAR (%): 80.79 -> 81.67Improved
add f-SPL (RKL) lossConv-Pool SER · MSP->IEMOCAP ActivationUAR (%): 80.79 -> 81.16No clear effect
add f-SPL (RKL) lossConv-Pool SER · IEMOCAP->MSP ActivationUAR (%): 72.74 -> 74.30Improved
add f-SPL loss (any f)Conv-Pool SER · IEMOCAP->MSP ValenceUAR (%): 61.31 -> 60.81 (KL); 60.44 (JS)Hurt
choice of f divergence for f-SPL (ablation)f-SPL · all four experimentsUAR (%)No clear effect
add f-SPL to cross-entropy trainingConv-Pool SER · MSP->IEMOCAP Valence and IEMOCAP->MSP Activationstability over epochsImproved

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