AlexNet is a deep convolutional neural network architecture originally developed for large-scale image classification, consisting of five convolutional layers followed by fully connected layers, which demonstrated landmark performance on the ImageNet benchmark. In the context of WiFi/CSI sensing and crowd counting research, AlexNet serves as an influential backbone architecture that researchers adapt for feature extraction and classification tasks, often by fine-tuning its pretrained weights on domain-specific data to leverage learned visual representations. Its significance lies in having popularized the use of deep CNNs as general-purpose feature extractors, inspiring subsequent architectures and transfer learning strategies that underpin many modern sensing and density estimation pipelines, though it has largely been succeeded by deeper variants such as VGGNet, ResNet, and GoogLeNet in state-of-the-art applications.
Source Papers
- A survey of recent advances in CNN-based single image crowd counting and density estimation ↗ — A survey of recent advances in CNN-based single image crowd
- A survey on CSI-based Wi-Fi sensing datasets and models with a focus on reproducibility ↗ — A survey on CSI-based Wi-Fi sensing datasets and models with
- Recent trends in crowd analysis: A review ↗ — Recent trends in crowd analysis: A review
- SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing ↗ — SenseFi: A library and benchmark on deep-learning-empowered