One‐shot video‐based person re‐identification with variance subsampling algorithm
Jing Zhao, Wenjing Yang, Mingke Yang, Wanrong Huang, Qiong Yang, Hongguang Zhang · Computer Animation and Virtual Worlds · 2020
Abstract Previous works propose the distance‐based sampling for unlabeled datapoints to address the few‐shot person re‐identification task, however, many selected samples may be assigned with wrong labels due to poor feature quality in these works, which negatively affects the learning procedure. In this article, we propose a novel sampling strategy to improve the quality of assigned pseudo‐labels, thus promoting the final performance. To illustrate, we first propose the concept of variance confidence to measure the credibility of pseudo‐labels, then we apply a novel variance subsampling algorithm to improve the accuracy of the selected sample labels. Our method combines distance confidence and variance confidence as a two‐round sampling criterion. Meanwhile, a variation decay strategy is used in our sampling process in combination with the actual distribution of features. We evaluate our approach on two publicly available datasets, MARS and DukeMTMC‐VideoReID, and achieve state‐of‐the‐art one‐shot performance.