Knowledge Commons of Institute of Automation,CAS
Learning Disentangled Attribute Representations for Robust Pedestrian Attribute Recognition | |
Jia, Jian1,2; Gao, Naiyu1,2; He, Fei1,2; Chen, Xiaotang1,2; Huang, Kaiqi1,2,3 | |
2022 | |
会议名称 | AAAI Conference on Artificial Intelligence |
会议录名称 | 36th AAAI Conference on Artificial Intelligence (AAAI) |
会议日期 | 2022 |
会议地点 | Virtual |
摘要 | Although various methods have been proposed for pedestrian attribute recognition, most studies follow the same feature learning mechanism, i.e., learning a shared pedestrian image feature to classify multiple attributes. However, this mechanism leads to low-confidence predictions and non-robustness of the model in the inference stage. In this paper, we investigate why this is the case. We mathematically discover that the central cause is that the optimal shared feature cannot maintain high similarities with multiple classifiers simultaneously in the context of minimizing classification loss. In addition, this feature learning mechanism ignores the spatial and semantic distinctions between different attributes. To address these limitations, we propose a novel disentangled attribute feature learning (DAFL) framework to learn a disentangled feature for each attribute, which exploits the semantic and spatial characteristics of attributes. The framework mainly consists of learnable semantic queries, a cascaded semantic-spatial cross-attention (SSCA) module, and a group attention merging (GAM) module. Specifically, based on learnable semantic queries, the cascaded SSCA module iteratively enhances the spatial localization of attribute-related regions and aggregates region features into multiple disentangled attribute features, used for classification and updating learnable semantic queries. The GAM module splits attributes into groups based on spatial distribution and utilizes reliable group attention to supervise query attention maps. Experiments on PETA, RAPv1, PA100k, and RAPv2 show that the proposed method performs favorably against state-of-the-art methods. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48741 |
专题 | 复杂系统认知与决策实验室_智能系统与工程 |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 2.CRISE, Institute of Automation, Chinese Academy of Sciences, Beijing, China 3.CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Jia, Jian,Gao, Naiyu,He, Fei,et al. Learning Disentangled Attribute Representations for Robust Pedestrian Attribute Recognition[C],2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
DAFL-AAAI2022.pdf(1286KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论