Attention-Aware Adversarial Network for Person Re-Identification
AbstractPerson re-identification (re-ID) is a fundamental problem in the field of computer vision. The performance of deep learning-based person re-ID models suffers from a lack of training data. In this work, we introduce a novel image-specific data augmentation method on the feature map level to enforce feature diversity in the network. Furthermore, an attention assignment mechanism is proposed to enforce that the person re-ID classifier focuses on nearly all important regions of the input person image. To achieve this, a three-stage framework is proposed. First, a baseline classification network is trained for person re-ID. Second, an attention assignment network is proposed based on the baseline network, in which the attention module learns to suppress the response of the current detected regions and re-assign attentions to other important locations. By this means, multiple important regions for classification are highlighted by the attention map. Finally, the attention map is integrated in the attention-aware adversarial network (AAA-Net), which generates high-performance classification results with an adversarial training strategy. We evaluate the proposed method on two large-scale benchmark datasets, including Market1501 and DukeMTMC-reID. Experimental results show that our algorithm performs favorably against the state-of-the-art methods. View Full-Text
Share & Cite This Article
Shen, A.; Wang, H.; Wang, J.; Tan, H.; Liu, X.; Cao, J. Attention-Aware Adversarial Network for Person Re-Identification. Appl. Sci. 2019, 9, 1550.
Shen A, Wang H, Wang J, Tan H, Liu X, Cao J. Attention-Aware Adversarial Network for Person Re-Identification. Applied Sciences. 2019; 9(8):1550.Chicago/Turabian Style
Shen, Aihong; Wang, Huasheng; Wang, Junjie; Tan, Hongchen; Liu, Xiuping; Cao, Junjie. 2019. "Attention-Aware Adversarial Network for Person Re-Identification." Appl. Sci. 9, no. 8: 1550.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.