POAR：迈向开放词汇的行人属性识别
POAR: Towards Open Vocabulary Pedestrian Attribute Recognition
AI总结：
针对现实场景无法穷尽行人属性的问题，提出POAR框架，将其转化为图文搜索任务，利用Transformer图像编码器和多对多对比损失在部位级别建模，有效处理未见属性。
摘要：
行人属性识别（PAR）旨在预测监控系统中目标行人的属性。现有方法通过训练具有预定义属性类别的多标签分类器来解决PAR问题。然而，在现实世界中不可能穷尽所有行人属性。为了解决这个问题，我们开发了一种新颖的行人开放属性识别（POAR）框架。我们的核心思想是将POAR问题表述为图像-文本搜索问题。我们设计了一种基于Transformer并带有掩码策略的图像编码器。引入了一组属性令牌，以专注于特定的行人部位（例如，头部、上半身、下半身、脚等），并将相应的属性编码为视觉嵌入。每个属性类别被描述为自然语言句子并由文本编码器编码。然后，我们计算属性视觉嵌入和文本嵌入之间的相似度，以为输入图像寻找最佳属性描述。与为每个属性类别学习特定分类器的现有方法不同，我们在部位级别对行人进行建模，并探索搜索方法以处理未见属性。最后，由于一张行人图像可以包含多个属性，提出了一种带有掩码令牌的多对多对比（MTMC）损失来训练网络。在基准PAR数据集上以开放属性设置进行了大量实验。结果验证了所提出的POAR方法的有效性，该方法可以为POAR任务形成强大的基线。我们的代码可在https://github.com/IvyYZ/POAR获取。
英文摘要：
Pedestrian attribute recognition (PAR) aims to predict the attributes of a target pedestrian in a surveillance system. Existing methods address the PAR problem by training a multi-label classifier with predefined attribute classes. However, it is impossible to exhaust all pedestrian attributes in the real world. To tackle this problem, we develop a novel pedestrian open-attribute recognition (POAR) framework. Our key idea is to formulate the POAR problem as an image-text search problem. We design a Transformer-based image encoder with a masking strategy. A set of attribute tokens are introduced to focus on specific pedestrian parts (e.g., head, upper body, lower body, feet, etc.) and encode corresponding attributes into visual embeddings. Each attribute category is described as a natural language sentence and encoded by the text encoder. Then, we compute the similarity between the visual and text embeddings of attributes to find the best attribute descriptions for the input images. Different from existing methods that learn a specific classifier for each attribute category, we model the pedestrian at a part-level and explore the searching method to handle the unseen attributes. Finally, a many-to-many contrastive (MTMC) loss with masked tokens is proposed to train the network since a pedestrian image can comprise multiple attributes. Extensive experiments have been conducted on benchmark PAR datasets with an open-attribute setting. The results verified the effectiveness of the proposed POAR method, which can form a strong baseline for the POAR task. Our code is available at \url{https://github.com/IvyYZ/POAR}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
