# ASD: Towards Attribute Spatial Decomposition for Prior-Free Facial Attribute Recognition

arXiv: https://arxiv.org/abs/2210.13716 · HTML: https://mlsanity.com/paper/2210.13716/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 54 references that are in the map.
- First posted on arXiv 25 Oct 2022.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [TResNet: High Performance GPU-Dedicated Architecture](https://mlsanity.com/paper/2003.13630/) (2020)
- [Attribute2Image: Conditional Image Generation from Visual Attributes](https://mlsanity.com/paper/1512.00570/) (2015)
- [PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation](https://mlsanity.com/paper/2103.13173/) (2021)
- [Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach](https://mlsanity.com/paper/1706.00906/) (2017)
- [Disentangled Image Generation Through Structured Noise Injection](https://mlsanity.com/paper/2004.12411/) (2020)
- [MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes](https://mlsanity.com/paper/1603.07027/) (2016)
- [Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification](https://mlsanity.com/paper/2002.03683/) (2020)
- [Hierarchical Feature Embedding for Attribute Recognition](https://mlsanity.com/paper/2005.11576/) (2020)
- [The UU-Net: Reversible Face De-Identification for Visual Surveillance Video Footage](https://mlsanity.com/paper/2007.04316/) (2020)
- [Recognizing Part Attributes with Insufficient Data](https://mlsanity.com/paper/1908.03335/) (2019)
- [Slim-CNN: A Light-Weight CNN for Face Attribute Prediction](https://mlsanity.com/paper/1907.02157/) (2019)
- [Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis](https://mlsanity.com/paper/2004.09502/) (2020)
- [Improving Facial Attribute Recognition by Group and Graph Learning](https://mlsanity.com/paper/2105.13825/) (2021)
- [TNTC: two-stream network with transformer-based complementarity for gait-based emotion recognition](https://mlsanity.com/paper/2110.13708/) (2021)

## Abstract (arXiv)

Representing the spatial properties of facial attributes is a vital challenge for facial attribute recognition (FAR). Recent advances have achieved the reliable performances for FAR, benefiting from the description of spatial properties via extra prior information. However, the extra prior information might not be always available, resulting in the restricted application scenario of the prior-based methods. Meanwhile, the spatial ambiguity of facial attributes caused by inherent spatial diversities of facial parts is ignored. To address these issues, we propose a prior-free method for attribute spatial decomposition (ASD), mitigating the spatial ambiguity of facial attributes without any extra prior information. Specifically, assignment-embedding module (AEM) is proposed to enable the procedure of ASD, which consists of two operations: attribute-to-location assignment and location-to-attribute embedding. The attribute-to-location assignment first decomposes the feature map based on latent factors, assigning the magnitude of attribute components on each spatial location. Then, the assigned attribute components from all locations to represent the global-level attribute embeddings. Furthermore, correlation matrix minimization (CMM) is introduced to enlarge the discriminability of attribute embeddings. Experimental results demonstrate the superiority of ASD compared with state-of-the-art prior-based methods, while the reliable performance of ASD for the case of limited training data is further validated.