TransFA: Transformer-based Representation for Face Attribute Evaluation

TL;DR

TransFA introduces a transformer-based approach for face attribute evaluation that leverages inter-attribute correlations and face identity information, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a novel transformer-based framework that models attribute inter-correlation and integrates face identity features for improved attribute evaluation.

Findings

Achieves superior performance on multiple face attribute benchmarks.

Effectively models attribute inter-correlation using a multi-branch transformer.

Incorporates face identity information to enhance attribute discriminability.

Abstract

Face attribute evaluation plays an important role in video surveillance and face analysis. Although methods based on convolution neural networks have made great progress, they inevitably only deal with one local neighborhood with convolutions at a time. Besides, existing methods mostly regard face attribute evaluation as the individual multi-label classification task, ignoring the inherent relationship between semantic attributes and face identity information. In this paper, we propose a novel \textbf{trans}former-based representation for \textbf{f}ace \textbf{a}ttribute evaluation method (\textbf{TransFA}), which could effectively enhance the attribute discriminative representation learning in the context of attention mechanism. The multiple branches transformer is employed to explore the inter-correlation between different attributes in similar semantic regions for attribute feature learning. Specially, the hierarchical identity-constraint attribute loss is designed to train the end-to-end architecture, which could further integrate face identity discriminative information to boost performance. Experimental results on multiple face attribute benchmarks demonstrate that the proposed TransFA achieves superior performances compared with state-of-the-art methods.