# Improving Facial Attribute Prediction using Semantic Segmentation

arXiv: https://arxiv.org/abs/1704.08740 · HTML: https://mlsanity.com/paper/1704.08740/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2017.

## Built on by (most cited first, 16 of 16)

- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion](https://mlsanity.com/paper/2312.10692/) (2023)
- [RoI Tanh-polar Transformer Network for Face Parsing in the Wild](https://mlsanity.com/paper/2102.02717/) (2021)
- [Label2Label: A Language Modeling Framework for Multi-Attribute Learning](https://mlsanity.com/paper/2207.08677/) (2022)
- [NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research](https://mlsanity.com/paper/2211.11747/) (2022)
- [Improving Facial Attribute Recognition by Group and Graph Learning](https://mlsanity.com/paper/2105.13825/) (2021)
- [Estimation of BMI from Facial Images using Semantic Segmentation based Region-Aware Pooling](https://mlsanity.com/paper/2104.04733/) (2021)
- [FacialGAN: Style Transfer and Attribute Manipulation on Synthetic Faces](https://mlsanity.com/paper/2110.09425/) (2021)
- [Generalized Face Anti-Spoofing via Multi-Task Learning and One-Side Meta Triplet Loss](https://mlsanity.com/paper/2211.15955/) (2022)
- [Tasks Structure Regularization in Multi-Task Learning for Improving Facial Attribute Prediction](https://mlsanity.com/paper/2108.04353/) (2021)
- [POAR: Towards Open Vocabulary Pedestrian Attribute Recognition](https://mlsanity.com/paper/2303.14643/) (2023)
- [SynMotor: A Benchmark Suite for Object Attribute Regression and Multi-task Learning](https://mlsanity.com/paper/2301.05027/) (2023)
- [Biased Binary Attribute Classifiers Ignore the Majority Classes](https://mlsanity.com/paper/2403.14435/) (2024)
- [Multi-Attribute Vision Transformers are Efficient and Robust Learners](https://mlsanity.com/paper/2402.08070/) (2024)
- [Mask-Guided Multi-Task Network for Face Attribute Recognition](https://mlsanity.com/paper/2601.01408/) (2026)
- [FAR-AMTN: Attention Multi-Task Network for Face Attribute Recognition](https://mlsanity.com/paper/2601.01537/) (2026)

## Abstract (arXiv)

Attributes are semantically meaningful characteristics whose applicability widely crosses category boundaries. They are particularly important in describing and recognizing concepts where no explicit training example is given, textite.g., zero-shot learning. Additionally, since attributes are human describable, they can be used for efficient human-computer interaction. In this paper, we propose to employ semantic segmentation to improve facial attribute prediction. The core idea lies in the fact that many facial attributes describe local properties. In other words, the probability of an attribute to appear in a face image is far from being uniform in the spatial domain. We build our facial attribute prediction model jointly with a deep semantic segmentation network. This harnesses the localization cues learned by the semantic segmentation to guide the attention of the attribute prediction to the regions where different attributes naturally show up. As a result of this approach, in addition to recognition, we are able to localize the attributes, despite merely having access to image level labels (weak supervision) during training. We evaluate our proposed method on CelebA and LFWA datasets and achieve superior results to the prior arts. Furthermore, we show that in the reverse problem, semantic face parsing improves when facial attributes are available. That reaffirms the need to jointly model these two interconnected tasks.