通过删减无效图像标记，实现高效面部情绪识别。
Sparse Attention to Emotion: Efficient Facial Emotion Recognition via Token Reduction
- 仅保留关键面部区域的图像标记，减少计算量。
- 删除90%标记后仍达顶尖准确率，计算复杂度降90%。
- 适合边缘设备部署，兼顾精度与效率。
面部情绪识别（FER）在生物识别、健康及人机交互等领域具有重要意义。现有基于视觉变换器的方法存在二次复杂度 $/mathcal{O}(N^2)$，其中 $N$ 为输入序列长度，难以在边缘设备部署。本文提出假设：FER无需全部面部信息，眼睛、嘴部及部分脸颊等特定区域已具备判别性。基于此，我们提出稀疏情绪注意力（SAE），舍弃对情绪无贡献的图像标记，同时保持高精度并大幅降低计算成本。实验表明，即使移除90%的图像标记，SAE在RAF-DB数据集上仍达到领先性能，计算复杂度最高降低90%，成为轻量级面部情绪识别的新标杆。
原文摘要 · Abstract (English)
Facial Emotion Recognition (FER) is an important task that has significant implications across various fields such as biometrics, health, and human-computer interaction. Current Vision Transformer-based approaches display quadratic complexity $\mathcal{O}(N^2)$, with N being the input sequence length, making them cumbersome to deploy at the edge. In this paper, we hypothesize that the FER task does not necessarily require all facial information to correctly interpret emotional states, as specific regions such as the eyes, the mouth, and parts of the cheeks carry discriminative information that can be sufficient to recognize emotions. Based on this, we propose Sparse Attention to Emotion (SAE), a model that discards image tokens that have no added value to the emotional context, while preserving good accuracy and achieving a significant gain in computational cost. Surprisingly, even after suppressing 90\% of the image tokens, our model achieves competitive accuracy to state of the art methods at much lower cost, providing a lightweight Facial Emotion Recognition approach. Experimental results demonstrate that SAE achieves new state of the art results on the RAF-DB dataset while reducing the computational complexity by up to 90\%.
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。