English

General Image Descriptors for Open World Image Retrieval using ViT CLIP

Computer Vision and Pattern Recognition 2022-10-21 v1 Artificial Intelligence

Abstract

The Google Universal Image Embedding (GUIE) Challenge is one of the first competitions in multi-domain image representations in the wild, covering a wide distribution of objects: landmarks, artwork, food, etc. This is a fundamental computer vision problem with notable applications in image retrieval, search engines and e-commerce. In this work, we explain our 4th place solution to the GUIE Challenge, and our "bag of tricks" to fine-tune zero-shot Vision Transformers (ViT) pre-trained using CLIP.

Keywords

Cite

@article{arxiv.2210.11141,
  title  = {General Image Descriptors for Open World Image Retrieval using ViT CLIP},
  author = {Marcos V. Conde and Ivan Aerlic and Simon Jégou},
  journal= {arXiv preprint arXiv:2210.11141},
  year   = {2022}
}

Comments

ECCV 2022 Instance-Level Recognition Workshop

R2 v1 2026-06-28T04:04:21.106Z