Cross Domain Knowledge Transfer for Unsupervised Vehicle Re-identification

Abstract

Vehicle re-identification (reID) is to identify a target vehicle in different cameras with non-overlapping views. When deploy the well-trained model to a new dataset directly, there is a severe performance drop because of differences among datasets named domain bias. To address this problem, this paper proposes an domain adaptation framework which contains an image-to-image translation network named vehicle transfer generative adversarial network (VTGAN) and an attention-based feature learning network (ATTNet). VTGAN could make images from the source domain (well-labeled) have the style of target domain (unlabeled) and preserve identity information of source domain. To further improve the domain adaptation ability for various backgrounds, ATTNet is proposed to train generated images with the attention structure for vehicle reID. Comprehensive experimental results clearly demonstrate that our method achieves excellent performance on VehicleID dataset.

References in corpus (6)

• A Discriminatively Learned CNN Embedding for Person Re-identification
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Multi-View Spectral Clustering via Structured Low-Rank Matrix Factorization
• Unsupervised Cross-Domain Image Generation
• Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval
• 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification