# Pedestrian Attribute Recognition as Label-balanced Multi-label Learning

arXiv: https://arxiv.org/abs/2405.04858 · HTML: https://mlsanity.com/paper/2405.04858/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 56 references that are in the map.
- First posted on arXiv 8 May 2024.

## Builds on (most cited first, 30 of 31)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Concrete Dropout](https://mlsanity.com/paper/1705.07832/) (2017)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Dataset Augmentation in Feature Space](https://mlsanity.com/paper/1702.05538/) (2017)
- [Implicit Semantic Data Augmentation for Deep Networks](https://mlsanity.com/paper/1909.12220/) (2019)
- [MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2103.12579/) (2021)
- [HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis](https://mlsanity.com/paper/1709.09930/) (2017)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection](https://mlsanity.com/paper/2203.02194/) (2022)
- [Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification](https://mlsanity.com/paper/1710.06555/) (2017)
- [Pedestrian Attribute Recognition: A Survey](https://mlsanity.com/paper/1901.07474/) (2019)
- [Rethinking Feature Distribution for Loss Functions in Image Classification](https://mlsanity.com/paper/1803.02988/) (2018)
- [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)
- [Label2Label: A Language Modeling Framework for Multi-Attribute Learning](https://mlsanity.com/paper/2207.08677/) (2022)
- [Localization Guided Learning for Pedestrian Attribute Recognition](https://mlsanity.com/paper/1808.09102/) (2018)
- [Person Re-identification Meets Image Search](https://mlsanity.com/paper/1502.02171/) (2015)
- [PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2304.07230/) (2023)
- [Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method](https://mlsanity.com/paper/2005.11909/) (2020)
- [Out of Distribution Data Detection Using Dropout Bayesian Neural Networks](https://mlsanity.com/paper/2202.08985/) (2022)
- [UPAR: Unified Pedestrian Attribute Recognition and Person Retrieval](https://mlsanity.com/paper/2209.02522/) (2022)
- [A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2307.15252/) (2023)
- [Generative Adversarial Models for People Attribute Recognition in Surveillance](https://mlsanity.com/paper/1707.02240/) (2017)
- [Learning Transferable Pedestrian Representation from Multimodal Information Supervision](https://mlsanity.com/paper/2304.05554/) (2023)

## Built on by (most cited first, 8 of 8)

- [Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework](https://mlsanity.com/paper/2408.09720/) (2024)
- [RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework](https://mlsanity.com/paper/2504.10018/) (2025)
- [Pedestrian Attribute Recognition via Hierarchical Cross-Modality HyperGraph Learning](https://mlsanity.com/paper/2509.22331/) (2025)
- [EvRainDrop: HyperGraph-guided Completion for Effective Frame and Event Stream Aggregation](https://mlsanity.com/paper/2511.21439/) (2025)
- [When Gender is Hard to See: Multi-Attribute Support for Long-Range Recognition](https://mlsanity.com/paper/2512.06426/) (2025)
- [UniPAR: A Unified Framework for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2603.05114/) (2026)
- [PFM-VEPAR: Prompting Foundation Models for RGB-Event Camera based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2603.19565/) (2026)
- [Is Spurious Correlation Removal Always Learnable?](https://mlsanity.com/paper/2606.12930/) (2026)

## Abstract (arXiv)

Rooting in the scarcity of most attributes, realistic pedestrian attribute datasets exhibit unduly skewed data distribution, from which two types of model failures are delivered: (1) label imbalance: model predictions lean greatly towards the side of majority labels; (2) semantics imbalance: model is easily overfitted on the under-represented attributes due to their insufficient semantic diversity. To render perfect label balancing, we propose a novel framework that successfully decouples label-balanced data re-sampling from the curse of attributes co-occurrence, i.e., we equalize the sampling prior of an attribute while not biasing that of the co-occurred others. To diversify the attributes semantics and mitigate the feature noise, we propose a Bayesian feature augmentation method to introduce true in-distribution novelty. Handling both imbalances jointly, our work achieves best accuracy on various popular benchmarks, and importantly, with minimal computational budget.