# Bi-Encoder Cascades for Efficient Image Search

arXiv: https://arxiv.org/abs/2303.15595 · HTML: https://mlsanity.com/paper/2303.15595/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2023.

## Built on by (most cited first, 1 of 1)

- [Semantic Leakage from Image Embeddings](https://mlsanity.com/paper/2601.22929/) (2026)

## Abstract (arXiv)

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.