English

A Generative Approach for Wikipedia-Scale Visual Entity Recognition

Computer Vision and Pattern Recognition 2024-03-22 v2

Abstract

In this paper, we address web-scale visual entity recognition, specifically the task of mapping a given query image to one of the 6 million existing entities in Wikipedia. One way of approaching a problem of such scale is using dual-encoder models (eg CLIP), where all the entity names and query images are embedded into a unified space, paving the way for an approximate k-NN search. Alternatively, it is also possible to re-purpose a captioning model to directly generate the entity names for a given image. In contrast, we introduce a novel Generative Entity Recognition (GER) framework, which given an input image learns to auto-regressively decode a semantic and discriminative ``code'' identifying the target entity. Our experiments demonstrate the efficacy of this GER paradigm, showcasing state-of-the-art performance on the challenging OVEN benchmark. GER surpasses strong captioning, dual-encoder, visual matching and hierarchical classification baselines, affirming its advantage in tackling the complexities of web-scale recognition.

Keywords

Cite

@article{arxiv.2403.02041,
  title  = {A Generative Approach for Wikipedia-Scale Visual Entity Recognition},
  author = {Mathilde Caron and Ahmet Iscen and Alireza Fathi and Cordelia Schmid},
  journal= {arXiv preprint arXiv:2403.02041},
  year   = {2024}
}

Comments

CVPR2024

R2 v1 2026-06-28T15:08:22.995Z