Neural network multi-attribute facial encoder and decoder

A computer program product embodied in a non-transitory computer readable medium for machine learning, the computer program product comprising code which causes one or more processors to perform operations of:

• obtaining a facial image for processing on a neural network;
• encoding the facial image into two or more orthogonal feature subspaces, wherein the encoding is performed by a single, trained encoder, wherein the encoder is a downsampling encoder, wherein orthogonality of the feature subspaces is established using metrics, and wherein the orthogonality enables separability of the feature subspaces;
• and
• generating embeddings for two or more attributes of the facial image, wherein the embeddings are generated using one or more copies of the single, trained encoder.

A computer system for machine learning comprising:

• a memory which stores instructions;
• one or more processors coupled to the memory wherein the one or more processors, when executing the instructions which are stored, are configured to:
• obtain a facial image for processing on a neural network;
• encode the facial image into two or more orthogonal feature subspaces, wherein the encoding is performed by a single, trained encoder, wherein the encoder is a downsampling encoder, wherein orthogonality of the feature subspaces is established using metrics, and wherein the orthogonality enables separability of the feature subspaces;
• and
• generate embeddings for two or more attributes of the facial image, wherein the embeddings are generated using one or more copies of the single, trained encoder.