Domain adaptation for machine learning models

In a digital medium environment for adapting a document classification model to a new domain, a method implemented by at least one computing device, the method comprising:

• adapting the document classification model to the new domain by:
• identifying a data type of training data used to generate the document classification model;
• obtaining a new domain document having a data type that is different from the data type of the training data;
• causing the document classification model to generate a feature representation describing a plurality of different feature channels that each describe different content included in the new domain document;
• generating a probability distribution for each pixel of the new domain document based on the feature representation, the probability distribution describing a likelihood of the pixel depicting each of the plurality of different feature channels;
• determining a loss function by comparing the probability distribution to a ground truth for the new domain document;
• and
• refining one or more parameters of the document classification model using the loss function;
• and
• outputting the document classification model with the one or more parameters as a domain-agnostic document classification model.

A system comprising:

• one or more processors;
• and
• a computer-readable medium having instructions stored thereon that are executable by the one or more processors to perform operations comprising:
• receiving a machine learning model configured to process first domain data and generate an output that classifies features of the first domain data;
• training the machine learning model to process data of a second domain that is different from the first domain by:
• causing the machine learning model to generate, from the second domain data, a feature representation that describes features of the second domain data;
• generating a probability distribution for each of a plurality of discrete regions of the second domain data based on the feature representation, the probability distribution describing a likelihood of the discrete region including each of the features described by the feature representation;
• computing a loss function by comparing the probability distribution to a ground truth classification for the second domain data;
• and
• refining at least one parameter of the machine learning model using the loss function;
• and
• outputting the machine learning model with its at least one parameter as the trained machine learning model.