用轻量模型和去偏策略提升复杂环境下表情识别准确率
InsideOut: An EfficientNetV2-S Based Deep Learning Framework for Robust Multi-Class Facial Emotion Recognition
- 基于EfficientNetV2-S构建轻量框架，结合迁移学习与数据增强
- 在FER2013上达62.8%准确率，宏F1为0.590，优于传统CNN
- 适合需要可复现、低资源部署的表情识别场景
面部情绪识别（FER）是情感计算的关键任务，广泛应用于人机交互、在线教育、医疗及安全系统。尽管深度学习取得进展，仍面临遮挡、光照变化、姿态差异、类内细微差异以及数据集不平衡等问题，导致少数情绪识别困难。本文提出InsideOut框架，基于EfficientNetV2-S，采用迁移学习、强数据增强和不平衡感知优化。该方法对FER2013图像进行标准化处理，使用分层采样与增强策略，并通过类别加权损失微调轻量分类头以缓解分布偏差。在FER2013数据集上达到62.8%的准确率和0.590的宏平均F1值，性能优于传统CNN基线。研究证明，高效架构结合定制化不平衡处理，可实现实用、透明且可复现的面部情绪识别方案。
原文摘要 · Abstract (English)
Facial Emotion Recognition (FER) is a key task in affective computing, enabling applications in human-computer interaction, e-learning, healthcare, and safety systems. Despite advances in deep learning, FER remains challenging due to occlusions, illumination and pose variations, subtle intra-class differences, and dataset imbalance that hinders recognition of minority emotions. We present InsideOut, a reproducible FER framework built on EfficientNetV2-S with transfer learning, strong data augmentation, and imbalance-aware optimization. The approach standardizes FER2013 images, applies stratified splitting and augmentation, and fine-tunes a lightweight classification head with class-weighted loss to address skewed distributions. InsideOut achieves 62.8% accuracy with a macro averaged F1 of 0.590 on FER2013, showing competitive results compared to conventional CNN baselines. The novelty lies in demonstrating that efficient architectures, combined with tailored imbalance handling, can provide practical, transparent, and reproducible FER solutions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。