Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Emotion RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
In this work we aim to obtain computationally-efficient uncertainty estimates with deep networks. For this, we propose a modified knowledge distillation procedure that achieves state-of-the-art uncertainty estimates both…
Knowledge DistillationIn-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models
Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We prop…
Few-Shot LearningIn-Context LearningLanguage ModelingLanguage ModellingHow Is Uncertainty Propagated in Knowledge Distillation?
Knowledge distillation transfers behavior from a teacher to a student model, but the process is inherently stochastic: teacher outputs, student training, and student inference can all be random. Collapsing these uncertai…
Knowledge DistillationUncertainty in multitask learning: joint representations for probabilistic MR-only radiotherapy planning
Multi-task neural network architectures provide a mechanism that jointly integrates information from distinct sources. It is ideal in the context of MR-only radiotherapy planning as it can jointly regress a synthetic CT …
Bayesian InferenceBayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors
When incorporating deep neural networks into robotic systems, a major challenge is the lack of uncertainty measures associated with their output predictions. Methods for uncertainty estimation in the output of deep objec…
Objectobject-detectionObject Detection