Person Reidentification by Multiscale Feature Representation Learning With Random Batch Feature Mask
Yong Wu, Kun Zhang, Di Wu, Chao Wang, Changan Yuan, Xiao Qin, Tao Zhu, Yuchuan Du, Hanli Wang, De-Shuang Huang
Abstract
Person reidentification (PReID) has received increasing attention due to its significant importance in intelligent video surveillance. However, most existing multiscale feature learning methods embed the multiscale feature extraction modules for PReID, which increases the complexity of the inference network and reduces the timeliness. Moreover, jointly using the small-scale and large-scale features to learn feature representations may weaken the local detailed features extraction and spatial information learning. Besides, some attentive local features are often suppressed when introducing the attention mechanisms for deep PReID models. To address these issues, a deep model with multiscale feature representation learning (MFRL) and random batch feature mask (RBFM) is proposed for PReID in this study. To ensure the feature representations discriminability and spatial information learning, two identity losses are adopted to supervise the small-scale and large-scale features learning in the MFRL module, respectively. To alleviate the situation of local attentive features being suppressed by using attention mechanisms, RBFM branch with random feature block dropping strategy which can learn the attentive local feature representations. The proposed methods are only performed in the training phase and discarded in the testing phase, thus, enhancing the effectiveness of the model. Our model achieves the state-of-the-art on the popular benchmark data sets, including Market-1501, DukeMTMC-reID, and CUHK03. Besides, we conduct a set of ablation experiments to verify the effectiveness of the proposed methods.