Metric Embedding Sub-discrimination Study

by   Ryan Furlong, et al.

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 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 sub-discrimination 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 a high accuracy rate, notably 99.3%, 99.3% and 94.1% for gender, skin tone, and age, respectively. Intra class tests show more mixed results with more nuanced attributes like emotions not being reliably classified, while more distinct attributes such as thick-framed glasses and beards, achieving 97.2% and 95.8% accuracy, respectively.


page 11

page 13


Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification

This paper addresses the task of zero-shot image classification. The key...

Beyond Correlation: A Path-Invariant Measure for Seismogram Similarity

Similarity search is a popular technique for seismic signal processing, ...

Discriminative Embedding Autoencoder with a Regressor Feedback for Zero-Shot Learning

Zero-shot learning (ZSL) aims to recognize the novel object categories u...

Preserving Semantic Relations for Zero-Shot Learning

Zero-shot learning has gained popularity due to its potential to scale r...

Learning Structured Semantic Embeddings for Visual Recognition

Numerous embedding models have been recently explored to incorporate sem...

Boosted Semantic Embedding based Discriminative Feature Generation for Texture Analysis

Learning discriminative features is crucial for various robotic applicat...

Please sign up or login with your details

Forgot password? Click here to reset