# PANDA: Pose Aligned Networks for Deep Attribute Modeling

arXiv: https://arxiv.org/abs/1311.5591 · HTML: https://mlsanity.com/paper/1311.5591/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2013.

## Built on by (most cited first, 23 of 23)

- [SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation](https://mlsanity.com/paper/2308.11509/) (2023)
- [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)
- [Label2Label: A Language Modeling Framework for Multi-Attribute Learning](https://mlsanity.com/paper/2207.08677/) (2022)
- [Multi-label Iterated Learning for Image Classification with Label Ambiguity](https://mlsanity.com/paper/2111.12172/) (2021)
- [Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning](https://mlsanity.com/paper/2302.11102/) (2023)
- [Facial-Sketch Synthesis: A New Challenge](https://mlsanity.com/paper/2112.15439/) (2021)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception](https://mlsanity.com/paper/2312.05525/) (2023)
- [Improving Facial Attribute Recognition by Group and Graph Learning](https://mlsanity.com/paper/2105.13825/) (2021)
- [Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2404.17929/) (2024)
- [Task-adaptive Q-Face](https://mlsanity.com/paper/2405.09059/) (2024)
- [Learning Discriminative Representations for Multi-Label Image Recognition](https://mlsanity.com/paper/2107.11159/) (2021)
- [Tasks Structure Regularization in Multi-Task Learning for Improving Facial Attribute Prediction](https://mlsanity.com/paper/2108.04353/) (2021)
- [Stochastic Block-ADMM for Training Deep Networks](https://mlsanity.com/paper/2105.00339/) (2021)
- [ImageSig: A signature transform for ultra-lightweight image recognition](https://mlsanity.com/paper/2205.06929/) (2022)
- [SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks](https://mlsanity.com/paper/2410.07857/) (2024)
- [Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning](https://mlsanity.com/paper/2604.26873/) (2026)
- [Weakly Supervised Recovery of Semantic Attributes](https://mlsanity.com/paper/2103.11888/) (2021)
- [A Facial Feature Discovery Framework for Race Classification Using Deep Learning](https://mlsanity.com/paper/2104.02471/) (2021)
- [Learning a Discriminant Latent Space with Neural Discriminant Analysis](https://mlsanity.com/paper/2107.06209/) (2021)
- [TransFA: Transformer-based Representation for Face Attribute Evaluation](https://mlsanity.com/paper/2207.05456/) (2022)
- [Mask-Guided Multi-Task Network for Face Attribute Recognition](https://mlsanity.com/paper/2601.01408/) (2026)

## Abstract (arXiv)

We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion. Convolutional Neural Nets (CNN) have been shown to perform very well on large scale object recognition problems. In the context of attribute classification, however, the signal is often subtle and it may cover only a small part of the image, while the image is dominated by the effects of pose and viewpoint. Discounting for pose variation would require training on very large labeled datasets which are not presently available. Part-based models, such as poselets and DPM have been shown to perform well for this problem but they are limited by shallow low-level features. We propose a new method which combines part-based models and deep learning by training pose-normalized CNNs. We show substantial improvement vs. state-of-the-art methods on challenging attribute classification tasks in unconstrained settings. Experiments confirm that our method outperforms both the best part-based methods on this problem and conventional CNNs trained on the full bounding box of the person.