# Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition

arXiv: https://arxiv.org/abs/2108.04228 · HTML: https://mlsanity.com/paper/2108.04228/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 39 references that are in the map.
- First posted on arXiv 21 Jul 2021.

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild](https://mlsanity.com/paper/1708.03985/) (2017)
- [Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace](https://mlsanity.com/paper/1910.04855/) (2019)
- [Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond](https://mlsanity.com/paper/1804.10938/) (2018)
- [Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning](https://mlsanity.com/paper/2002.06470/) (2020)
- [MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices](https://mlsanity.com/paper/1804.07573/) (2018)
- [Analysing Affective Behavior in the First ABAW 2020 Competition](https://mlsanity.com/paper/2001.11409/) (2020)
- [Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework](https://mlsanity.com/paper/2103.15792/) (2021)
- [Self-Distillation Amplifies Regularization in Hilbert Space](https://mlsanity.com/paper/2002.05715/) (2020)
- [Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study](https://mlsanity.com/paper/2105.03790/) (2021)
- [Analysing Affective Behavior in the second ABAW2 Competition](https://mlsanity.com/paper/2106.15318/) (2021)
- [Ensemble Distribution Distillation](https://mlsanity.com/paper/1905.00076/) (2019)
- [Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network](https://mlsanity.com/paper/1910.11111/) (2019)
- [Aff-Wild2: Extending the Aff-Wild Database for Affect Recognition](https://mlsanity.com/paper/1811.07770/) (2018)
- [Self-Distillation as Instance-Specific Label Smoothing](https://mlsanity.com/paper/2006.05065/) (2020)
- [From Facial Expression Recognition to Interpersonal Relation Prediction](https://mlsanity.com/paper/1609.06426/) (2016)
- [Multitask Emotion Recognition with Incomplete Labels](https://mlsanity.com/paper/2002.03557/) (2020)
- [MIMAMO Net: Integrating Micro- and Macro-motion for Video Emotion Recognition](https://mlsanity.com/paper/1911.09784/) (2019)
- [MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection](https://mlsanity.com/paper/2010.13886/) (2020)

## Built on by (most cited first, 21 of 21)

- [Transformer-based Multimodal Information Fusion for Facial Expression Analysis](https://mlsanity.com/paper/2203.12367/) (2022)
- [Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition](https://mlsanity.com/paper/2212.05463/) (2022)
- [A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition](https://mlsanity.com/paper/2203.14779/) (2022)
- [UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup](https://mlsanity.com/paper/2209.08928/) (2022)
- [Multi-modal Facial Affective Analysis based on Masked Autoencoder](https://mlsanity.com/paper/2303.10849/) (2023)
- [Audio-Visual Fusion for Emotion Recognition in the Valence-Arousal Space Using Joint Cross-Attention](https://mlsanity.com/paper/2209.09068/) (2022)
- [Frame-level Prediction of Facial Expressions, Valence, Arousal and Action Units for Mobile Devices](https://mlsanity.com/paper/2203.13436/) (2022)
- [Recursive Joint Cross-Modal Attention for Multimodal Fusion in Dimensional Emotion Recognition](https://mlsanity.com/paper/2403.13659/) (2024)
- [Joint Multimodal Transformer for Emotion Recognition in the Wild](https://mlsanity.com/paper/2403.10488/) (2024)
- [Multiple Emotion Descriptors Estimation at the ABAW3 Challenge](https://mlsanity.com/paper/2203.12845/) (2022)
- [An Ensemble Approach for Facial Expression Analysis in Video](https://mlsanity.com/paper/2203.12891/) (2022)
- [Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the Wild](https://mlsanity.com/paper/2407.12927/) (2024)
- [Continuous-Time Audiovisual Fusion with Recurrence vs. Attention for In-The-Wild Affect Recognition](https://mlsanity.com/paper/2203.13285/) (2022)
- [Efficient Multi-task Uncertainties for Joint Semantic Segmentation and Monocular Depth Estimation](https://mlsanity.com/paper/2402.10580/) (2024)
- [Facial Expression Classification using Fusion of Deep Neural Network in Video for the 3rd ABAW3 Competition](https://mlsanity.com/paper/2203.12899/) (2022)
- [Lightweight Toxicity Detection in Spoken Language: A Transformer-based Approach for Edge Devices](https://mlsanity.com/paper/2304.11408/) (2023)
- [Multimodal Fusion Method with Spatiotemporal Sequences and Relationship Learning for Valence-Arousal Estimation](https://mlsanity.com/paper/2403.12425/) (2024)
- [Multitask Emotion Recognition Model with Knowledge Distillation and Task Discriminator](https://mlsanity.com/paper/2203.13072/) (2022)
- [An Ensemble Approach for Multiple Emotion Descriptors Estimation Using Multi-task Learning](https://mlsanity.com/paper/2207.10878/) (2022)
- [Reweighted Mixup for Subpopulation Shift](https://mlsanity.com/paper/2304.04148/) (2023)
- [Conformal Prediction in Multi-User Settings: An Evaluation](https://mlsanity.com/paper/2312.05195/) (2023)

## Abstract (arXiv)

When recognizing emotions, subtle nuances in displays of emotion generate ambiguity or uncertainty in emotion perception. Emotion uncertainty has been previously interpreted as inter-rater disagreement among multiple annotators. In this paper, we consider a more common and challenging scenario: modeling emotion uncertainty when only single emotion labels are available. From a Bayesian perspective, we propose to use deep ensembles to capture uncertainty for multiple emotion descriptors, i.e., action units, discrete expression labels and continuous descriptors. We further apply iterative self-distillation. Iterative distillation over multiple generations significantly improves performance in both emotion recognition and uncertainty estimation. Our method generates single student models that provide accurate estimates of uncertainty for in-domain samples and a student ensemble that can detect out-of-domain samples. Our experiments on emotion recognition and uncertainty estimation using the Aff-wild2 dataset demonstrate that our algorithm gives more reliable uncertainty estimates than both Temperature Scaling and Monte Carol Dropout.