轻量级人脸识别模型，提升法证场景下复杂条件的准确率。
ForensicNet: Lightweight Attention-Enhanced MobileNetV2 for Automated Face Identification
- 用MobileNetV2+CBAM注意力模块提取关键特征
- 在68类1.5万张图像上达92.4%准确率，仅需2.1 GFLOPs
- 适合移动端实时法证监控，抗光照、遮挡和姿态变化
在法证环境中，由于姿态变化、光照差异、遮挡及标注数据不足，自动识别嫌疑人极具挑战。本文提出ForensicNet，一种轻量级深度学习框架，通过引入注意力机制增强特征学习。该模型结合MobileNetV2主干网络与卷积块注意力模块（CBAM），在保持计算效率的同时提升判别性特征提取能力。采用两阶段迁移学习策略，配合自适应层解冻机制，改善域适应性并减少过拟合。实验使用LFW和SCFace等公开数据集，包含15,000张面部图像，覆盖68个身份类别。所提模型在准确性（92.4%）、精确率（90.8%）和召回率（89.5%）上优于AlexNet、ResNet-50和MobileNetV2等基线模型。此外，单次推理仅需2.1 GFLOPs，适用于实时法证监控应用。
原文摘要 · Abstract (English)
In forensic environments, automated identification of perpetrators is difficult due to pose changes, changes in light, occlusion, and lack of labeled data. This paper presents ForensicNet, a lightweight deep learning framework for forensic face recognition that enhances attention. The suggested model combines the MobileNetV2 backbone with Convolutional Block Attention Modules (CBAM) to improve the learning of discriminative features while maintaining computational speed. A two-phase transfer learning strategy with adaptive layer unfreezing is used to improve domain adaptation and reduce overfitting. This study used publicly available datasets such as LFW and SCFace, with 15,000 facial images spanning 68 identity classes. The proposed model outperforms baseline architectures such as AlexNet, ResNet-50, and MobileNetV2, with an accuracy of 92.4%, a precision of 90.8%, and a recall of 89.5%. Additionally, the framework requires only 2.1 GFLOPs per inference, and hence can be used in real-time forensic surveillance applications.
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。