Face Attribute Prediction Using Off-the-Shelf CNN Features

TL;DR

This paper explores using pre-trained CNN features combined with traditional face localization to predict face attributes, achieving results comparable to state-of-the-art methods on large datasets.

Contribution

It introduces a novel approach of leveraging off-the-shelf CNN features at different levels for face attribute prediction, simplifying the pipeline.

Findings

Comparable performance to state-of-the-art on LFWA and CelebA datasets

Demonstrates effectiveness of off-the-shelf CNN features for attribute prediction

Raises questions on leveraging pre-trained CNNs for new tasks

Abstract

Predicting attributes from face images in the wild is a challenging computer vision problem. To automatically describe face attributes from face containing images, traditionally one needs to cascade three technical blocks --- face localization, facial descriptor construction, and attribute classification --- in a pipeline. As a typical classification problem, face attribute prediction has been addressed using deep learning. Current state-of-the-art performance was achieved by using two cascaded Convolutional Neural Networks (CNNs), which were specifically trained to learn face localization and attribute description. In this paper, we experiment with an alternative way of employing the power of deep representations from CNNs. Combining with conventional face localization techniques, we use off-the-shelf architectures trained for face recognition to build facial descriptors. Recognizing that the describable face attributes are diverse, our face descriptors are constructed from different levels of the CNNs for different attributes to best facilitate face attribute prediction. Experiments on two large datasets, LFWA and CelebA, show that our approach is entirely comparable to the state-of-the-art. Our findings not only demonstrate an efficient face attribute prediction approach, but also raise an important question: how to leverage the power of off-the-shelf CNN representations for novel tasks.