Achieving 3D Attention via Triplet Squeeze and Excitation Block

2025/05/09 by Maan Alhazmi, Alhazmi, Maan, Abdulrahman Altahhan +1
Computer Science · Neuroscience · Psychology · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Emotion and Mood Recognition #FOS: Computer and information sciences #Face Recognition and Perception #Face recognition and analysis #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2505.05943

openalex publication_date 2025/05/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

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 78.27% on the popular FER2013 dataset, a new feat for this dataset.

Citations

• A ConvNet for the 2020s
• A ConvNet for the 2020s
• Attention Mechanisms in Computer Vision: A Survey
• Local Multi-Head Channel Self-Attention for Facial Expression Recognition
• Facial Emotion Recognition: State of the Art Performance on FER2013
• Training data-efficient image transformers & distillation through attention
• FcaNet: Frequency Channel Attention Networks
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Rotate to Attend: Convolutional Triplet Attention Module
• ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
• ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
• Gated Channel Transformation for Visual Recognition
• An Attentive Survey of Attention Models
• SRM : A Style-based Recalibration Module for Convolutional Neural Networks
• Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network
• Global Second-order Pooling Convolutional Networks
• CBAM: Convolutional Block Attention Module
• BAM: Bottleneck Attention Module
• Non-local Neural Networks
• Squeeze-and-Excitation Networks
• Attention Is All You Need
• Residual Attention Network for Image Classification
• Densely Connected Convolutional Networks
• Deep Residual Learning for Image Recognition
• Spatial Transformer Networks
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Going Deeper with Convolutions
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Recurrent Models of Visual Attention
• Challenges in Representation Learning: A report on three machine learning contests
• ImageNet classification with deep convolutional neural networks
• Gradient-based learning applied to document recognition

Related

• Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition
• Squeeze-and-Excitation Networks
• ExpNet: Landmark-Free, Deep, 3D Facial Expressions
• A Lightweight Attention-based Deep Network via Multi-Scale Feature Fusion for Multi-View Facial Expression Recognition
• Lossless Attention in Convolutional Networks for Facial Expression Recognition in the Wild