Deep fusion of visual signatures for client-server facial analysis

TL;DR

This paper introduces a client-server facial analysis framework that merges various visual face features into a universal signature, enabling efficient and accurate face attribute recognition across different resource settings.

Contribution

It proposes a novel universal representation learning method to align and merge diverse face features into a single signature for improved client-server facial analysis.

Findings

Outperforms state-of-the-art methods with rich features.

Maintains competitive accuracy with simple features under resource constraints.

Validated on the CelebA dataset.

Abstract

Facial analysis is a key technology for enabling human-machine interaction. In this context, we present a client-server framework, where a client transmits the signature of a face to be analyzed to the server, and, in return, the server sends back various information describing the face e.g. is the person male or female, is she/he bald, does he have a mustache, etc. We assume that a client can compute one (or a combination) of visual features; from very simple and efficient features, like Local Binary Patterns, to more complex and computationally heavy, like Fisher Vectors and CNN based, depending on the computing resources available. The challenge addressed in this paper is to design a common universal representation such that a single merged signature is transmitted to the server, whatever be the type and number of features computed by the client, ensuring nonetheless an optimal performance. Our solution is based on learning of a common optimal subspace for aligning the different face features and merging them into a universal signature. We have validated the proposed method on the challenging CelebA dataset, on which our method outperforms existing state-of-the-art methods when rich representation is available at test time, while giving competitive performance when only simple signatures (like LBP) are available at test time due to resource constraints on the client.