# TransFA: Transformer-based Representation for Face Attribute Evaluation

arXiv: https://arxiv.org/abs/2207.05456 · HTML: https://mlsanity.com/paper/2207.05456/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 65 references that are in the map.
- First posted on arXiv 12 Jul 2022.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Transformer Tracking](https://mlsanity.com/paper/2103.15436/) (2021)
- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [Deep Imbalanced Learning for Face Recognition and Attribute Prediction](https://mlsanity.com/paper/1806.00194/) (2018)
- [Pedestrian Attribute Recognition: A Survey](https://mlsanity.com/paper/1901.07474/) (2019)
- [ViDT: An Efficient and Effective Fully Transformer-based Object Detector](https://mlsanity.com/paper/2110.03921/) (2021)
- [Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach](https://mlsanity.com/paper/1706.00906/) (2017)
- [Multi-Graph Transformer for Free-Hand Sketch Recognition](https://mlsanity.com/paper/1912.11258/) (2019)
- [Face Recognition Accuracy Across Demographics: Shining a Light Into the Problem](https://mlsanity.com/paper/2206.01881/) (2022)
- [PANDA: Pose Aligned Networks for Deep Attribute Modeling](https://mlsanity.com/paper/1311.5591/) (2013)
- [Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification](https://mlsanity.com/paper/2002.03683/) (2020)
- [The UU-Net: Reversible Face De-Identification for Visual Surveillance Video Footage](https://mlsanity.com/paper/2007.04316/) (2020)
- [A Deep Cascade Network for Unaligned Face Attribute Classification](https://mlsanity.com/paper/1709.03851/) (2017)
- [Segment-based Methods for Facial Attribute Detection from Partial Faces](https://mlsanity.com/paper/1801.03546/) (2018)

## Abstract (arXiv)

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 transformer-based representation for face attribute evaluation method (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.