A Discriminatively Learned CNN Embedding for Person Reidentification

Abstract

Abstract-In this paper, we revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e.,verification and identification models. The two models have their respective advantages and limitations due to different loss functions. In this paper, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a siamese network that simultaneously computes the identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two input images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus making full usage of the re-ID annotations.Our method can be easily applied on different pre-trained networks. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show our architecture can also be applied in image retrieval.

Learning deep features from body and parts for person re-identification in camera networks

“…5. The proposed DFBP largely improves the performance compared with the previous reported results, such as 10.51% mAP, 13.72% rank-1 accuracy in [19] and 48.42% mAP, 54.42% rank-1 accuracy in [16]. These results indicate that the proposed DFBP could also learn the discriminative features under different viewpoints.…”

“…2a. In order to connect the two networks, we employ a non-parametric layer called square layer [16] to compare the features f 1 , f 2 . The input of square layer is f 1 and f 2 , and the output is formulated as:…”

“…The performance of the proposed DFBP is better than the part-based features and body-based features, because we make full use of the complementarity between the part-based features and body-based features. The proposed DFBP and Verif.-Identif [16] utilize the verification and identification models. Noticeably, the proposed DFBP outperforms the Verif.-Identif in all situations due to considering the structural information of pedestrian by learning part-based features.…”

“…Xiao et al [15] jointly trained a identification model using multiple datasets and proposed a new dropout function to deal with a large number of classes. Furthermore, Zheng et al [16] combined the verification and identification models by jointly learning three loss functions.…”

SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification

“…Both images with suppressed BGs (our generated images) and images with full BGs are respectively fed into the two individual streams of DA-2S. Unlike previous 2-stream methods (e.g., [2,5,40]), we propose Inter-Stream Densely Connection (ISDC) modules as new components used between the two streams of DA-2S. With ISDCs, more gradients produced by the final objective function can participate to strengthen the relationship between signals coming from two different streams in the back-propagation.…”