Adaptive Transfer Network for Cross-Domain Person Re-Identification

By Jiawei Liu, Zhengjun Zha, Di Chen, Richang Hong, Meng Wang. 2019

284 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning (2022, background): “In domain adaptation [20, 43], residual adapter [18, 25, 26] is proposed to learn style information related to new domains, thus improving the overall generalization performance of the network.”
Group-aware Label Transfer for Domain Adaptive Person Re-identification (2021, methodology): “Existing UDA ReID approaches [14, 26, 35, 45, 55] typically include three steps: feature pre-training with labeled source domain data, clustering-based pseudo-label prediction for the target domain data, and feature representation learning/fine-tuning with the pseudo-labels.”
Image-to-Image Translation: Methods and Applications (2021, methodology): “I2I methods can also contribute to other visual tasks, such as transfer learning for reinforcement learning [217], image registration [38], domain adaptation [29], [30], [31], person re-identification [218], [219], [220], [221], [222], image segmentation [7], [8], [9], facial geometry reconstruction”
Learning to Generate Novel Domains for Domain Generalization (2020, unknown): “We follow the recent unsupervised domain adaptation (UDA) methods in the person re-ID literature [58,59,32] and experiment with Market1501→Duke and Duke→Market1501.”
Omni-Scale Feature Learning for Person Re-Identification (2019, methodology): “5 ATNet [32] Market1501 + Duke (U ) 45.”
Style Normalization and Restitution for Generalizable Person Re-Identification (2020, methodology): “UDAbased ReID methods can be roughly divided into three categories: style transfer [3, 44, 26], attribute recognition [43, 49, 33], and target-domain pseudo label estimation [5, 37, 58, 40, 52, 50].”
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification (2019, background): “Most of the existing work is categorized in two ways as follows: pose transfer [18, 22, 6] and style transfer [32, 19, 5, 31].”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “These methods include PUL [208], CAMEL [206], PTGAN [118], TJ-AIDL [109], HHL [215], DAS [122], MAR [210], ENC [105], ATNet [216], PAUL [157], SBGAN [217], UCDA [219], CASC [211], PDA [119], CR-GAN [218], PAST [220], SSG [213].”