Incremental Deep Hidden Attribute Learning
Incremental Deep Hidden Attribute Learning
复制标题
DOI：
10.1145/3240508.3240510
复制
发表时间：
2018-10
期刊：
影响因子：
--
通讯作者：
Zheng Wang;X. Bai;Mang Ye;S. Satoh
中科院分区：
文献类型：
--
作者：
Zheng Wang;X. Bai;Mang Ye;S. Satoh
人的再识别是在非重叠摄像机视角下匹配人图像的关键技术。由于视觉特征对环境变化的敏感性，人们开始研究“短发”或“长发”等语义属性来代表人的外表，以提高重新识别性能。通常，训练语义属性表示需要大量的标注样本，这限制了其在大规模实际应用中的适用性。为了减轻对注释工作的依赖，我们提出了一个新的人表示与隐藏的属性挖掘潜在的信息，从视觉特征在无监督的方式。特别地，自动编码器模型被插入到深度学习网络中以组成深度隐藏属性网络（DHA-Net）。学习的隐藏属性表示保留了语义属性的鲁棒性，同时继承了视觉特征的区分能力。在公共数据集上进行的实验验证了DHA-Net的有效性。在两个大规模数据集上，即，Market-1501和DukeMTMC-reID的仿真结果表明，该方法优于现有方法。
Person re-identifcation is a key technique to match person images captured in non-overlapping camera views. Due to the sensitivity of visual features to environmental changes, semantic attributes, such as "short-hair" or "long-hair", begin to be investigated to represent person's appearance to improve the re-identifcation performance. Generally, training semantic attribute representations requires massive annotated samples, which limits the applicability on the large-scale practical applications. To alleviate the reliance on annotation efforts, we propose a new person representation with hidden attributes by mining latent information from visual feature in an unsupervised manner. In particular, an auto-encoder model is plugged-in to the deep learning network to compose a Deep Hidden Attribute Network (DHA-Net). The learnt hidden attribute representation preserves the robustness of semantic attributes and simultaneously inherits the discrimination ability of visual features. Experiments conducted on public datasets have validated the effectiveness of DHA-Net. On two large-scale datasets, i.e., Market-1501 and DukeMTMC-reID, the proposed method outperforms the state-of-the-art methods.