TL;DR本研究提出了一种使用代理数据集来解决领域自适应问题的方法,该数据集经过良好构建可以有效捕捉到具有相似分布的目标数据集的模型性能排名,并在 Person Re-identification 任务中进行了验证。
Abstract
Consider a scenario where we are supplied with a number of ready-to-use
models trained on a certain source domain and hope to directly apply the most
appropriate ones to different target domains based on the models' relative
performance. Ideally we should annotate a validation set for