# Reinforced Pedestrian Attribute Recognition with Group Optimization Reward

arXiv: https://arxiv.org/abs/2205.14042 · HTML: https://mlsanity.com/paper/2205.14042/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 70 references that are in the map.
- First posted on arXiv 21 May 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward](https://mlsanity.com/paper/1801.00054/) (2017)
- [HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis](https://mlsanity.com/paper/1709.09930/) (2017)
- [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)
- [Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey](https://mlsanity.com/paper/2108.11510/) (2021)
- [A Richly Annotated Dataset for Pedestrian Attribute Recognition](https://mlsanity.com/paper/1603.07054/) (2016)
- [Attribute Recognition by Joint Recurrent Learning of Context and Correlation](https://mlsanity.com/paper/1709.08553/) (2017)
- [Deep Reinforcement Learning for Imbalanced Classification](https://mlsanity.com/paper/1901.01379/) (2019)
- [Localization Guided Learning for Pedestrian Attribute Recognition](https://mlsanity.com/paper/1808.09102/) (2018)
- [Semantic Regularisation for Recurrent Image Annotation](https://mlsanity.com/paper/1611.05490/) (2016)
- [Hierarchical Object Detection with Deep Reinforcement Learning](https://mlsanity.com/paper/1611.03718/) (2016)
- [Distraction-Aware Feature Learning for Human Attribute Recognition via Coarse-to-Fine Attention Mechanism](https://mlsanity.com/paper/1911.11351/) (2019)
- [Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model](https://mlsanity.com/paper/1707.06089/) (2017)
- [Dynamic Face Video Segmentation via Reinforcement Learning](https://mlsanity.com/paper/1907.01296/) (2019)
- [Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization](https://mlsanity.com/paper/1611.05603/) (2016)
- [Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization](https://mlsanity.com/paper/2106.06485/) (2021)
- [Efficient Pedestrian Detection in Top-View Fisheye Images Using Compositions of Perspective View Patches](https://mlsanity.com/paper/2009.02711/) (2020)
- [An Attention-Based Deep Learning Model for Multiple Pedestrian Attributes Recognition](https://mlsanity.com/paper/2004.01110/) (2020)
- [Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2004.03164/) (2020)
- [Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints](https://mlsanity.com/paper/2011.06798/) (2020)
- [Sequential Person Recognition in Photo Albums with a Recurrent Network](https://mlsanity.com/paper/1611.09967/) (2016)

## Abstract (arXiv)

Pedestrian Attribute Recognition (PAR) is a challenging task in intelligent video surveillance. Two key challenges in PAR include complex alignment relations between images and attributes, and imbalanced data distribution. Existing approaches usually formulate PAR as a recognition task. Different from them, this paper addresses it as a decision-making task via a reinforcement learning framework. Specifically, PAR is formulated as a Markov decision process (MDP) by designing ingenious states, action space, reward function and state transition. To alleviate the inter-attribute imbalance problem, we apply an Attribute Grouping Strategy (AGS) by dividing all attributes into subgroups according to their region and category information. Then we employ an agent to recognize each group of attributes, which is trained with Deep Q-learning algorithm. We also propose a Group Optimization Reward (GOR) function to alleviate the intra-attribute imbalance problem. Experimental results on the three benchmark datasets of PETA, RAP and PA100K illustrate the effectiveness and competitiveness of the proposed approach and demonstrate that the application of reinforcement learning to PAR is a valuable research direction.