6 citations · 11 across the 3 of their papers we have counts for
7 papers · 1 filter
An Embedding is Worth a Thousand Noisy Labels
Francesco Di Salvo, Sebastian Doerrich, Ines Rieger +1
The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust a…
CorrLoss: Integrating Co-Occurrence Domain Knowledge for Affect Recognition
Ines Rieger, Jaspar Pahl, Bettina Finzel +1
Neural networks are widely adopted, yet the integration of domain knowledge is still underutilized. We propose to integrate domain knowledge about co-occurring facial movements as…
Multi-label Learning with Missing Values using Combined Facial Action Unit Datasets
Jaspar Pahl, Ines Rieger, Dominik Seuss
Facial action units allow an objective, standardized description of facial micro movements which can be used to describe emotions in human faces. Annotating data for action units i…
Unique Class Group Based Multi-Label Balancing Optimizer for Action Unit Detection
Ines Rieger, Jaspar Pahl, Dominik Seuss
Balancing methods for single-label data cannot be applied to multi-label problems as they would also resample the samples with high occurrences. We propose to reformulate this prob…
Verifying Deep Learning-based Decisions for Facial Expression Recognition
Ines Rieger, Rene Kollmann, Bettina Finzel +2
Neural networks with high performance can still be biased towards non-relevant features. However, reliability and robustness is especially important for high-risk fields such as cl…
Multi-Label Class Balancing Algorithm for Action Unit Detection
Jaspar Pahl, Ines Rieger, Dominik Seuss
Isolated facial movements, so-called Action Units, can describe combined emotions or physical states such as pain. As datasets are limited and mostly imbalanced, we present an appr…