Person re-identification (re-ID) aims at recognizing the same person from images taken across different cameras. On the other hand, cross-dataset/domain re-ID focuses on leveraging labeled image data from source to target domains, while target-domain training data are without label information. In order to introduce discriminative ability and to generalize the re-ID model to the unsupervised target domain, our proposed Pose Disentanglement and Adaptation Network (PDA-Net) learns deep image representation with pose and domain information properly disentangled. Our model allows pose-guided image recovery and translation by observing images from either domain, without predefined pose category nor identity supervision. Our qualitative and quantitative results on two benchmark datasets confirm the effectiveness of our approach and its superiority over state-of-the-art cross-dataset re-ID approaches.

No abstract

Person re-identification (Re-ID) aims at recognizing the same person from images taken across different cameras. To address this task, one typically requires a large amount labeled data for training an effective Re-ID model, which might not be practical for real-world applications. To alleviate this limitation, we choose to exploit a sufficient amount of pre-existing labeled data from a different (auxiliary) dataset. By jointly considering such an auxiliary dataset and the dataset of interest (but without label information), our proposed adaptation and re-identification network (ARN) performs unsupervised domain adaptation, which leverages information across datasets and derives domain-invariant features for Re-ID purposes. In our experiments, we verify that our network performs favorably against state-of-the-art unsupervised Re-ID approaches, and even outperforms a number of baseline Re-ID methods which require fully supervised data for training.

Most existing person re-identification (ReID) methods have good feature representations to distinguish pedestrians with deep convolutional neural network (CNN) and metric learning methods. However, these works concentrate on the similarity between encoder output and ground-truth, ignoring the correlation between input and encoder output, which affects the performance of identifying different pedestrians. To address this limitation, We design a Deep InfoMax (DIM) network to maximize the mutual information (MI) between the input image and encoder output, which doesn't need any auxiliary labels. To evaluate the effectiveness of the DIM network, we propose end-to-end Global-DIM and Local-DIM models. Additionally, the DIM network provides a new solution for cross-dataset unsupervised ReID issue as it needs no extra labels. The experiments prove the superiority of MI theory on the ReID issue, which achieves the state-of-the-art results.