# PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition

arXiv: https://arxiv.org/abs/2304.07230 · HTML: https://mlsanity.com/paper/2304.07230/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 74 references that are in the map.
- First posted on arXiv 14 Apr 2023.

## Builds on (most cited first, 30 of 42)

- [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)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [General Multi-label Image Classification with Transformers](https://mlsanity.com/paper/2011.14027/) (2020)
- [TResNet: High Performance GPU-Dedicated Architecture](https://mlsanity.com/paper/2003.13630/) (2020)
- [HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis](https://mlsanity.com/paper/1709.09930/) (2017)
- [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023)
- [Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer](https://mlsanity.com/paper/2112.02466/) (2021)
- [A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization](https://mlsanity.com/paper/2201.09206/) (2022)
- [Deep Imbalanced Attribute Classification using Visual Attention Aggregation](https://mlsanity.com/paper/1807.03903/) (2018)
- [Pedestrian Attribute Recognition: A Survey](https://mlsanity.com/paper/1901.07474/) (2019)
- [Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization](https://mlsanity.com/paper/1910.04562/) (2019)
- [A Richly Annotated Dataset for Pedestrian Attribute Recognition](https://mlsanity.com/paper/1603.07054/) (2016)
- [Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2109.05686/) (2021)
- [Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting](https://mlsanity.com/paper/2107.03576/) (2021)
- [Notes on Noise Contrastive Estimation and Negative Sampling](https://mlsanity.com/paper/1410.8251/) (2014)
- [Attribute Recognition by Joint Recurrent Learning of Context and Correlation](https://mlsanity.com/paper/1709.08553/) (2017)
- [Explainable Person Re-Identification with Attribute-guided Metric Distillation](https://mlsanity.com/paper/2103.01451/) (2021)
- [Localization Guided Learning for Pedestrian Attribute Recognition](https://mlsanity.com/paper/1808.09102/) (2018)

## Built on by (most cited first, 19 of 19)

- [Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion](https://mlsanity.com/paper/2312.10692/) (2023)
- [SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation Paradigm](https://mlsanity.com/paper/2312.01640/) (2023)
- [An Empirical Study of Mamba-based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2407.10374/) (2024)
- [Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework](https://mlsanity.com/paper/2408.09720/) (2024)
- [Pedestrian Attribute Recognition as Label-balanced Multi-label Learning](https://mlsanity.com/paper/2405.04858/) (2024)
- [SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition](https://mlsanity.com/paper/2312.06049/) (2023)
- [RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework](https://mlsanity.com/paper/2504.10018/) (2025)
- [Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2404.17929/) (2024)
- [Domain Consistency Representation Learning for Lifelong Person Re-Identification](https://mlsanity.com/paper/2409.19954/) (2024)
- [MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection](https://mlsanity.com/paper/2403.15209/) (2024)
- [SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition](https://mlsanity.com/paper/2407.20920/) (2024)
- [ViTA-PAR: Visual and Textual Attribute Alignment with Attribute Prompting for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2506.01411/) (2025)
- [Pedestrian Attribute Recognition via Hierarchical Cross-Modality HyperGraph Learning](https://mlsanity.com/paper/2509.22331/) (2025)
- [SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks](https://mlsanity.com/paper/2410.07857/) (2024)
- [Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time Adaptation](https://mlsanity.com/paper/2507.00462/) (2025)
- [A Data-Centric Approach to Pedestrian Attribute Recognition: Synthetic Augmentation via Prompt-driven Diffusion Models](https://mlsanity.com/paper/2509.02099/) (2025)
- [ASGNet: Adaptive Spectrum Guidance Network for Automatic Polyp Segmentation](https://mlsanity.com/paper/2604.14755/) (2026)
- [Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning](https://mlsanity.com/paper/2604.26873/) (2026)
- [PFM-VEPAR: Prompting Foundation Models for RGB-Event Camera based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2603.19565/) (2026)

## Abstract (arXiv)

Pedestrian attribute recognition (PAR) has received increasing attention because of its wide application in video surveillance and pedestrian analysis. Extracting robust feature representation is one of the key challenges in this task. The existing methods mainly use the convolutional neural network (CNN) as the backbone network to extract features. However, these methods mainly focus on small discriminative regions while ignoring the global perspective. To overcome these limitations, we propose a pure transformer-based multi-task PAR network named PARFormer, which includes four modules. In the feature extraction module, we build a transformer-based strong baseline for feature extraction, which achieves competitive results on several PAR benchmarks compared with the existing CNN-based baseline methods. In the feature processing module, we propose an effective data augmentation strategy named batch random mask (BRM) block to reinforce the attentive feature learning of random patches. Furthermore, we propose a multi-attribute center loss (MACL) to enhance the inter-attribute discriminability in the feature representations. In the viewpoint perception module, we explore the impact of viewpoints on pedestrian attributes, and propose a multi-view contrastive loss (MCVL) that enables the network to exploit the viewpoint information. In the attribute recognition module, we alleviate the negative-positive imbalance problem to generate the attribute predictions. The above modules interact and jointly learn a highly discriminative feature space, and supervise the generation of the final features. Extensive experimental results show that the proposed PARFormer network performs well compared to the state-of-the-art methods on several public datasets, including PETA, RAP, and PA100K. Code will be released at https://github.com/xwf199/PARFormer.