Deep Learning: Image classification, feature visualization and transfer learning with Keras
Basic Colab demo
In this code, we are going to implement a basic image classifier:
In this code we are going to load pretrained image classification networks
Then using a pretrained network, feature extraction and visualization is conducted via t-SNE
In Transfer learning, we would like to leverage the knowledge learned by a source task to help learning another target task. For example, a well-trained, rich image classification network could be leveraged for another image target related task. Another example, the knowledge learned by a network trained on simulated environment can be transferred to a network for the real environment. Basically, there are two basic scenarios for neural networks transfer learning:
A well known example for transfer learning is to load the already trained large scale classification VGG network that is able to classify images into one of 1000 classes, and use it for another task such as classification of special medical images.
Image search engines: Generally speaking, search engine usually takes a query and returns results. Image search engines takes an input image as an image query, then the image search engine finds the "similar" images within its indexed database and returns them as the search result. How to measure similarity between two images?