Deep Multi-Task Transfer Network for Cross Domain Person Re-Identification

Abstract

As a prominent application of surveillance video analysis, person re-identification attracts much more research attention recently. Existing person re-identification models often focus on supervision by the pedestrian identity annotation, while it has limited scalability in realistic. Though several unsupervised person re-identification researches pay attention to solve this problem, they are either clustering based or cross domain based approaches, where a conventional assumption of them is the identity number of the target dataset is acknowledged. To relax this hypothesis, we propose a Deep Multi-task Transfer Network (DMTNet) for cross domain person re-identification, which conduct classification, attribute attention and identification task between source and target domains. There are three main novelties in DMTNet, including clustering number estimating algorithm to learn prior knowledge from source data to estimate the identity number, attribute attention importance learning rather than directly utilizing attribute information, and a multi-task transfer learning mechanism to transfer specific tasks cross domains. To prove the superiority of our DMTNet, we implement several compared experiments on DukeMTMC-reID and Market-1501 datasets, which results show the advancement of our network. Moreover, the discussions for different modules also point out the significance of the specific tasks. INDEX TERMS Cross domain person re-identification, multi-task transfer, attribute attention, identity number estimating.

POISE: Efficient Cross-Domain Chinese Named Entity Recognization via Transfer Learning

“…Transfer learning can improve task performance by taking advantage of features from similar labels in these cases. Even on datasets with low-resource labels, it can sometimes yield an improvement over state-of-the-art results [5][6][7].…”

Attribute Memory Transfer Network for Unsupervised Cross-Domain Person Re-Identification

“…Firstly, the pedestrian samples from different domains present a distribution shift [29], [36], [45]. Several models attempt to narrow down the pixel-level and feature-level domain gaps using Generative Adversarial Network (GAN) [31], [36] and Mean Maximum Discrepancy (MMD) [4], [33], separately. The second aspect of the obstacles is the intra-domain variations, especially for target domain due to the lacking of identity labels.…”