English

Ranking Models in Unlabeled New Environments

Computer Vision and Pattern Recognition 2021-09-07 v2

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 model performance assessment on each new target environment, but such annotations are often very expensive. Under this circumstance, we introduce the problem of ranking models in unlabeled new environments. For this problem, we propose to adopt a proxy dataset that 1) is fully labeled and 2) well reflects the true model rankings in a given target environment, and use the performance rankings on the proxy sets as surrogates. We first select labeled datasets as the proxy. Specifically, datasets that are more similar to the unlabeled target domain are found to better preserve the relative performance rankings. Motivated by this, we further propose to search the proxy set by sampling images from various datasets that have similar distributions as the target. We analyze the problem and its solutions on the person re-identification (re-ID) task, for which sufficient datasets are publicly available, and show that a carefully constructed proxy set effectively captures relative performance ranking in new environments. Code is available at \url{https://github.com/sxzrt/Proxy-Set}.

Keywords

Cite

@article{arxiv.2108.10310,
  title  = {Ranking Models in Unlabeled New Environments},
  author = {Xiaoxiao Sun and Yunzhong Hou and Weijian Deng and Hongdong Li and Liang Zheng},
  journal= {arXiv preprint arXiv:2108.10310},
  year   = {2021}
}

Comments

13 pages, 10 figures, ICCV2021

R2 v1 2026-06-24T05:21:20.405Z