Residual Codean Autoencoder for Facial Attribute Analysis
This work addresses facial attribute prediction for applications like targeted marketing and law enforcement, but it appears incremental as it builds on existing autoencoder and shortcut connection techniques.
The paper tackles facial attribute prediction by proposing a novel R-Codean autoencoder that combines cosine similarity and Euclidean distance losses to incorporate both magnitude and direction of image vectors, and it includes shortcut connections and patch-based weighting; experimental results on CelebA and LFWA datasets demonstrate its efficacy.
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.