ImageNet is a large-scale visual recognition dataset containing millions of labeled images spanning thousands of categories, most commonly associated with the ImageNet Large Scale Visual Recognition Challenge (ILSVRC). In the context of WiFi CSI sensing research, ImageNet matters primarily as a source of pretrained model weights — deep architectures such as ResNet-18, ResNet-50, and ResNet-101, originally trained on ImageNet, are transferred and adapted to CSI signal representations, enabling researchers to leverage powerful feature extractors without training from scratch on limited sensing data. The key variant most referenced is the ILSVRC subset of 1.2 million images across 1,000 classes, and ImageNet-pretrained weights serve as a standard initialization baseline against which self-supervised and domain-specific pretraining strategies, such as CAPC, are evaluated to assess the value of task-specific representation learning for WiFi sensing.
Source Papers
- Context-Aware Predictive Coding: A Representation Learning Framework for WiFi Sensing ↗ — Context-Aware Predictive Coding: A Representation Learning F
- 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