English

Evaluating Contrastive Models for Instance-based Image Retrieval

Computer Vision and Pattern Recognition 2021-05-03 v1

Abstract

In this work, we evaluate contrastive models for the task of image retrieval. We hypothesise that models that are learned to encode semantic similarity among instances via discriminative learning should perform well on the task of image retrieval, where relevancy is defined in terms of instances of the same object. Through our extensive evaluation, we find that representations from models trained using contrastive methods perform on-par with (and outperforms) a pre-trained supervised baseline trained on the ImageNet labels in retrieval tasks under various configurations. This is remarkable given that the contrastive models require no explicit supervision. Thus, we conclude that these models can be used to bootstrap base models to build more robust image retrieval engines.

Keywords

Cite

@article{arxiv.2104.14939,
  title  = {Evaluating Contrastive Models for Instance-based Image Retrieval},
  author = {Tarun Krishna and Kevin McGuinness and Noel O'Connor},
  journal= {arXiv preprint arXiv:2104.14939},
  year   = {2021}
}

Comments

Accepted In Proceedings of the 2021 International Conference on Multimedia Retrieval (ICMR 21)

R2 v1 2026-06-24T01:40:09.428Z