One-Shot on-Device Learning for Image Classifiers Using Classification-by-Retrieval

Classification-by-retrieval is a simple method for developing a neural network-based classifier that does not require computationally intensive backpropagation training. This technology can be used to create a lightweight mobile model with as little as one picture per class or an on-device model that can classify tens of thousands of categories. For example, mobile models can […]

The post One-Shot on-Device Learning for Image Classifiers Using Classification-by-Retrieval appeared first on MarkTechPost.

ai shorts classification country editors pick featured guest post learning machine learning on-device learning retrieval tech tech news technology tensorflow usa