Residual Codean Autoencoder for Facial Attribute Analysis

TL;DR

This paper introduces the R-Codean autoencoder, a novel deep learning model that combines cosine similarity and shortcut connections for improved facial attribute prediction, demonstrating superior results on CelebA and LFWA datasets.

Contribution

The paper proposes a new autoencoder architecture that integrates cosine similarity loss and shortcut connections for enhanced facial attribute analysis.

Findings

Effective attribute prediction on CelebA and LFWA datasets

Improved feature learning through combined loss function

Enhanced model training with shortcut connections

Abstract

Facial attributes can provide rich ancillary information which can be utilized for different applications such as targeted marketing, human computer interaction, and law enforcement. This research focuses on facial attribute prediction using a novel deep learning formulation, termed as R-Codean autoencoder. The paper first presents Cosine similarity based loss function in an autoencoder which is then incorporated into the Euclidean distance based autoencoder to formulate R-Codean. The proposed loss function thus aims to incorporate both magnitude and direction of image vectors during feature learning. Further, inspired by the utility of shortcut connections in deep models to facilitate learning of optimal parameters, without incurring the problem of vanishing gradient, the proposed formulation is extended to incorporate shortcut connections in the architecture. The proposed R-Codean autoencoder is utilized in facial attribute prediction framework which incorporates patch-based weighting mechanism for assigning higher weights to relevant patches for each attribute. The experimental results on publicly available CelebA and LFWA datasets demonstrate the efficacy of the proposed approach in addressing this challenging problem.