Amazon announced a new capability today called Amazon Rekognition Custom Labels to help customers train machine learning models to understand a set of objects when there is a limited set of information.
Typically, machine learning models have to work on large data sets to learn something like what’s a picture of a dog, as opposed to some other animals. Amazon Rekognition Custom Labels can work with a limited data set to teach the algorithm a group of objects specific to a given use case.
“Instead of having to train a model from scratch, which requires specialized machine learning expertise and millions of high-quality labeled images, customers can now use Amazon Rekognition Custom Labels to achieve state-of-the-art performance for their unique image analysis needs,” the company wrote in a blog post announcing the new feature.
For example, you may want to teach the model to identify a set of engine parts, a limited set of information, which has a lot of meaning to a specific use case. Less information like this actually poses a problem for most machine learning models, but this feature has been designed specifically to learn from a smaller amount of data. Instead of hundreds or thousands of images, Amazon Rekognition Custom Labels can work with as few as ten images to learn to identify the object.
Amazon has gotten flack from the ACLU and shareholders in the past for selling Amazon Rekognition to law enforcement to help identify faces. This feature offers a more benign use of similar technology.
The new feature goes live next week on December 3rd, right in time for AWS re:Invent, the company’s customer conference taking place in Las Vegas.