Multi-Task Learning Using Uncertainty to Weigh Losses for Heterogeneous Face Attribute Estimation

TL;DR

This paper introduces a multi-task learning framework that uses uncertainty to balance loss functions for joint face attribute estimation, improving accuracy and efficiency on benchmark datasets.

Contribution

It presents a novel approach combining uncertainty weighting with shared feature extraction for heterogeneous face attribute estimation.

Findings

Outperforms state-of-the-art methods on multiple face attribute benchmarks.

Reduces training cost in multi-task face attribute estimation.

Validates effectiveness on edge systems.

Abstract

Face images contain a wide variety of attribute information. In this paper, we propose a generalized framework for joint estimation of ordinal and nominal attributes based on information sharing. We tackle the correlation problem between heterogeneous attributes using hard parameter sharing of shallow features, and trade-off multiple loss functions by considering homoskedastic uncertainty for each attribute estimation task. This leads to optimal estimation of multiple attributes of the face and reduces the training cost of multitask learning. Experimental results on benchmarks with multiple face attributes show that the proposed approach has superior performance compared to state of the art. Finally, we discuss the bias issues arising from the proposed approach in face attribute estimation and validate its feasibility on edge systems.