Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification

• DOI: 10.48550/arxiv.1804.09347
• Publication Date: 2018-01-01
• Authors: Yu-Jhe Li; Fu-En Yang; Yen‐Cheng Liu; Yu-Ying Yeh; Xiaofei Du; Yu-Chiang Frank Wang
• Keywords: Identification; Domain Adaptation; Transfer of learning; Baseline (sea); Labeled data

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 real-world applications. alleviate limitation, we choose to exploit sufficient of pre-existing (auxiliary) dataset. By jointly considering such auxiliary dataset and interest (but without label information), our proposed adaptation network (ARN) performs unsupervised domain adaptation, leverages information datasets derives domain-invariant features purposes. In experiments, verify that favorably against state-of-the-art approaches, even outperforms number baseline methods require fully supervised training.