Contrastive Language-Image Pre-training for the Italian Language

TL;DR

This paper introduces CLIP-Italian, a contrastive learning model for Italian that leverages 1.4 million image-text pairs, outperforming multilingual CLIP in image retrieval and zero-shot classification tasks.

Contribution

First CLIP model tailored for Italian, trained on a large dataset, demonstrating superior performance over multilingual models in specific tasks.

Findings

CLIP-Italian outperforms multilingual CLIP in image retrieval.

CLIP-Italian achieves better zero-shot classification results.

The model is trained on 1.4 million image-text pairs.

Abstract

CLIP (Contrastive Language-Image Pre-training) is a very recent multi-modal model that jointly learns representations of images and texts. The model is trained on a massive amount of English data and shows impressive performance on zero-shot classification tasks. Training the same model on a different language is not trivial, since data in other languages might be not enough and the model needs high-quality translations of the texts to guarantee a good performance. In this paper, we present the first CLIP model for the Italian Language (CLIP-Italian), trained on more than 1.4 million image-text pairs. Results show that CLIP-Italian outperforms the multilingual CLIP model on the tasks of image retrieval and zero-shot classification.