CLIP-Art: Contrastive Pre-Training for Fine-Grained Art Classification

07/30/2021

∙

by   Marcos V. Conde, et al.

∙

1

∙

share

Existing computer vision research in artwork struggles with artwork's fine-grained attributes recognition and lack of curated annotated datasets due to their costly creation. In this work, we use CLIP (Contrastive Language-Image Pre-Training) for training a neural network on a variety of art images and text pairs, being able to learn directly from raw descriptions about images, or if available, curated labels. Model's zero-shot capability allows predicting the most relevant natural language description for a given image, without directly optimizing for the task. Our approach aims to solve 2 challenges: instance retrieval and fine-grained artwork attribute recognition. We use the iMet Dataset, which we consider the largest annotated artwork dataset.