Reinforced Pedestrian Attribute Recognition with Group Optimization Reward

TL;DR

This paper introduces a reinforcement learning approach for pedestrian attribute recognition, addressing complex attribute-image relations and data imbalance issues through group optimization and a novel reward function, showing promising results on benchmarks.

Contribution

It formulates PAR as a decision-making process using reinforcement learning, incorporating attribute grouping and a new reward function to improve recognition accuracy.

Findings

Effective handling of attribute imbalance problems.

Superior performance on benchmark datasets.

Reinforcement learning proves valuable for PAR tasks.

Abstract

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.