{"slug": "forensicnet-lightweight-attention-enhanced-mobilenetv2-for-automated-face", "title": "ForensicNet: Lightweight Attention-Enhanced MobileNetV2 for Automated Face Identification", "summary": "ForensicNet, a lightweight deep learning framework combining MobileNetV2 with Convolutional Block Attention Modules, achieves 92.4% accuracy and 90.8% precision on face identification across 15,000 images from LFW and SCFace datasets, requiring only 2.1 GFLOPs per inference for real-time forensic surveillance.", "body_md": "arXiv:2607.16273v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/forensicnet-lightweight-attention-enhanced-mobilenetv2-for-automated-face", "canonical_source": "https://arxiv.org/abs/2607.16273", "published_at": "2026-07-21 04:00:00+00:00", "updated_at": "2026-07-21 04:08:17.551713+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "artificial-intelligence"], "entities": ["ForensicNet", "MobileNetV2", "Convolutional Block Attention Modules", "LFW", "SCFace", "AlexNet", "ResNet-50"], "alternates": {"html": "https://wpnews.pro/news/forensicnet-lightweight-attention-enhanced-mobilenetv2-for-automated-face", "markdown": "https://wpnews.pro/news/forensicnet-lightweight-attention-enhanced-mobilenetv2-for-automated-face.md", "text": "https://wpnews.pro/news/forensicnet-lightweight-attention-enhanced-mobilenetv2-for-automated-face.txt", "jsonld": "https://wpnews.pro/news/forensicnet-lightweight-attention-enhanced-mobilenetv2-for-automated-face.jsonld"}}