提出三元注意力模块，提升CNN在表情识别中的表现
Achieving 3D Attention via Triplet Squeeze and Excitation Block
- 将三元注意力与挤压激励结合，设计新型注意力块
- 在FER2013数据集上达78.27%准确率，创历史新高
- 适配多种CNN架构，尤其对ConvNeXt效果显著
ConvNeXt及其变体的兴起重新证明了基于CNN的模型在视觉任务中的适用性，使其成为图像分类及面部表情识别（FER）的重要方法。本文提出一组新模型，通过在ResNet18、DenseNet和ConvNeXt架构中引入四种不同变体的三元注意力与挤压-激励（TripSE）机制，验证其通用性和有效性。实验表明，将TripSE模块嵌入这些CNN模型可显著提升性能，尤其在ConvNeXt上表现突出。我们在CIFAR100、ImageNet、FER2013和AffectNet四个数据集上评估，其中ConvNeXt搭配TripSE在主流的FER2013数据集上达到78.27%的准确率，创下该数据集新纪录。
原文摘要 · Abstract (English)
The emergence of ConvNeXt and its variants has reaffirmed the conceptual and structural suitability of CNN-based models for vision tasks, re-establishing them as key players in image classification in general, and in facial expression recognition (FER) in particular. In this paper, we propose a new set of models that build on these advancements by incorporating a new set of attention mechanisms that combines Triplet attention with Squeeze-and-Excitation (TripSE) in four different variants. We demonstrate the effectiveness of these variants by applying them to the ResNet18, DenseNet and ConvNext architectures to validate their versatility and impact. Our study shows that incorporating a TripSE block in these CNN models boosts their performances, particularly for the ConvNeXt architecture, indicating its utility. We evaluate the proposed mechanisms and associated models across four datasets, namely CIFAR100, ImageNet, FER2013 and AffectNet datasets, where ConvNext with TripSE achieves state-of-the-art results with an accuracy of \textbf{78.27\%} on the popular FER2013 dataset, a new feat for this dataset.
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。