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 recognize tens of thousands of landmarks using classification-by-retrieval technology. Image recognition is divided into two methods: classification and retrieval. A common technique to object recognition is to construct a neural network classifier and train it using a considerable quantity of training data (often thousands of images or more).

Duplicate Docs Excel Report

None found

Similar Docs  Excel Report  more

None found