Common CNN-based Face Embedding Spaces are (Almost) Equivalent

by   David McNeely-White, et al.

CNNs are the dominant method for creating face embeddings for recognition. It might be assumed that, since these networks are distinct, complex, nonlinear functions, that their embeddings are network specific, and thus have some degree of anonymity. However, recent research has shown that distinct networks' features can be directly mapped with little performance penalty (median 1.9 reduction across 90 distinct mappings) in the context of the 1,000 object ImageNet recognition task. This finding has revealed that embeddings coming from different systems can be meaningfully compared, provided the mapping. However, prior work only considered networks trained and tested on a closed set classification task. Here, we present evidence that a linear mapping between feature spaces can be easily discovered in the context of open set face recognition. Specifically, we demonstrate that the feature spaces of four face recognition models, of varying architecture and training datasets, can be mapped between with no more than a 1.0 . This finding, which we also replicate on YouTube Faces, demonstrates that embeddings from different systems can be readily compared once the linear mapping is determined. In further analysis, fewer than 500 pairs of corresponding embeddings from two systems are required to calculate the full mapping between embedding spaces, and reducing the dimensionality of the mapping from 512 to 64 produces negligible performance penalty.



There are no comments yet.


page 1

page 2

page 3

page 4


Canonical Face Embeddings

We present evidence that many common convolutional neural networks (CNNs...

FaceNet: A Unified Embedding for Face Recognition and Clustering

Despite significant recent advances in the field of face recognition, im...

Recurrent Embedding Aggregation Network for Video Face Recognition

Recurrent networks have been successful in analyzing temporal data and h...

Probabilistic Face Embeddings

Embedding methods have achieved success in face recognition by comparing...

DeepVisage: Making face recognition simple yet with powerful generalization skills

Face recognition (FR) methods report significant performance by adopting...

Towards Protecting Face Embeddings in Mobile Face Verification Scenarios

This paper proposes PolyProtect, a method for protecting the sensitive f...

A Face Recognition System's Worst Morph Nightmare, Theoretically

It has been shown that Face Recognition Systems (FRSs) are vulnerable to...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.