General Image Descriptors For Open World Image Retrieval Using Vit CLIP
Marcos V. Conde, Ivan Aerlic, Simon Jégou . Arxiv 2022 – 1 citation
[Paper]
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.