Metric Embedding Sub-discrimination Study

Abstract

Deep metric learning is a technique used in a variety of discriminative tasks to achieve zero-shot, one-shot or few-shot learning. When applied, the system learns an embedding space where a non-parametric approach, such as Knearest neighbor (KNN), can be used to discriminate features during test time.This work focuses on investigating to what extent feature information contained within this embedding space can be used to carry out sub-discrimination in the feature space. The study shows that within a discrimination embedding, the information on the salient attributes needed to solve the problem of subdiscrimination is saved within the embedding and that this inherent information can be used to carry out sub-discriminative tasks. To demonstrate this, an embedding designed initially to discriminate faces is used to differentiate several attributes such as gender, age and skin tone, without any additional training.The study is split into two study cases: intra class discrimination where all the embeddings took into consideration are from the same identity; and extra class discrimination where the embeddings represent different identities. After the study, it is shown that it is possible to infer common attributes to different identities. The system can also perform extra class sub-discrimination with