Adaptive Transfer Network for Cross-Domain Person Re-Identification
Citations Over TimeTop 1% of 2019 papers
Abstract
Recent deep learning based person re-identification approaches have steadily improved the performance for benchmarks, however they often fail to generalize well from one domain to another. In this work, we propose a novel adaptive transfer network (ATNet) for effective cross-domain person re-identification. ATNet looks into the essential causes of domain gap and addresses it following the principle of "divide-and-conquer". It decomposes the complicated cross-domain transfer into a set of factor-wise sub-transfers, each of which concentrates on style transfer with respect to a certain imaging factor, e.g., illumination, resolution and camera view etc. An adaptive ensemble strategy is proposed to fuse factor-wise transfers by perceiving the affect magnitudes of various factors on images. Such "decomposition-and-ensemble" strategy gives ATNet the capability of precise style transfer at factor level and eventually effective transfer across domains. In particular, ATNet consists of a transfer network composed by multiple factor-wise CycleGANs and an ensemble CycleGAN as well as a selection network that infers the affects of different factors on transferring each image. Extensive experimental results on three widely-used datasets, i.e., Market-1501, DukeMTMC-reID and PRID2011 have demonstrated the effectiveness of the proposed ATNet with significant performance improvements over state-of-the-art methods.
Related Papers
- → Control Method for Electric Fuses with Controllable Fusing(2013)
- IC Fuse Blowing Method(2008)
- Analysis on the Reason of Fuse Melting Wrongly in Circuit and its Fault Excluding(2002)
- → Development of a Self-Destroying Fuse for Rocket Propelled Grenade Munitions(2019)
- → Fuses(1995)