BioKD: Selective Physiology-to-Video Knowledge Distillation via Reliability Gate for Emotion Recognition
Bojing Hou, Ruohao Li, Yitong Zhu, Hongjun Liu, Luwen Yu, Yuyang Wang
cs.LG
Submitted: 2026-08-06
License: http://creativecommons.org/licenses/by/4.0/
The gist: To address the limitations of video-based emotion recognition under ambiguous or socially masked behavioral cues, as well as the poor deployability of physiological signals, this paper proposes a
Terminology
Abstract
To address the limitations of video-based emotion recognition under ambiguous or socially masked behavioral cues, as well as the poor deployability of physiological signals, this paper proposes a reliability-aware physiology-to-video knowledge distillation framework, termed BioKD. The proposed framework leverages physiological signals as privileged information during training to guide a video-based student model in learning deep affective representations, while relying solely on non-intrusive video inputs at inference time. To cope with the high noise and instability of physiological teacher supervision caused by inter-subject variability, signal artifacts, and temporal inconsistency, BioKD incorporates a sample-wise reliability-aware gating mechanism together with a progressive distillation strategy. By adaptively regulating the strength of knowledge transfer, the framework suppresses negative transfer induced by unreliable physiological supervision and enables more stable cross-modal distillation. Experiments on DEAP and AMIGOS show that BioKD consistently outperforms representative baselines under both trial-wise and subject-wise evaluation protocols for valence and arousal recognition. For example, BioKD achieves 68.01% on DEAP (trial-wise arousal) and 65.29% under the more challenging subject-wise setting, demonstrating improved performance under a subject-independent evaluation setting. Further analyses show that BioKD effectively mitigates overconfident teacher errors and outperforms an entropy-only weighting strategy, confirming the importance of explicitly modeling supervision reliability. In addition, BioKD introduces no additional inference-time overhead relative to the same video student architecture and removes the need for physiological sensing and multimodal synchronization.
Sources
- Hierarchical MoE: Continuous Multimodal Emotion Recognition with Incomplete and Asynchronous Inputs
- Towards Consumer-Grade Cybersickness Prediction: Multi-Model Alignment for Real-Time Vision-Only Inference
- Distilling the Knowledge in a Neural Network
- Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
- A Comprehensive Survey on Knowledge Distillation
- FitNets: Hints for Thin Deep Nets
- Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
- Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks