English

Bi-Encoder Cascades for Efficient Image Search

Information Retrieval 2023-08-07 v2

Abstract

Modern neural encoders offer unprecedented text-image retrieval (TIR) accuracy, but their high computational cost impedes an adoption to large-scale image searches. To lower this cost, model cascades use an expensive encoder to refine the ranking of a cheap encoder. However, existing cascading algorithms focus on cross-encoders, which jointly process text-image pairs, but do not consider cascades of bi-encoders, which separately process texts and images. We introduce the small-world search scenario as a realistic setting where bi-encoder cascades can reduce costs. We then propose a cascading algorithm that leverages the small-world search scenario to reduce lifetime image encoding costs of a TIR system. Our experiments show cost reductions by up to 6x.

Keywords

Cite

@article{arxiv.2303.15595,
  title  = {Bi-Encoder Cascades for Efficient Image Search},
  author = {Robert Hönig and Jan Ackermann and Mingyuan Chi},
  journal= {arXiv preprint arXiv:2303.15595},
  year   = {2023}
}

Comments

Under review as a short paper at the ICCV '23 RCV workshop

R2 v1 2026-06-28T09:36:48.890Z