PaLI: A Jointly-Scaled Multilingual Language-Image Model

TL;DR

PaLI is a large-scale multilingual vision-language model that jointly scales and integrates visual and textual understanding, enabling state-of-the-art performance across diverse tasks and languages.

Contribution

This work introduces PaLI, a scalable, multimodal model that combines large pre-trained language and vision transformers for multilingual tasks.

Findings

PaLI achieves state-of-the-art results in vision and language tasks.

Joint scaling of vision and language components improves performance.

Training on 10 billion image-text pairs in over 100 languages enhances multilingual capabilities.

Abstract

Effective scaling and a flexible task interface enable large language models to excel at many tasks. We present PaLI (Pathways Language and Image model), a model that extends this approach to the joint modeling of language and vision. PaLI generates text based on visual and textual inputs, and with this interface performs many vision, language, and multimodal tasks, in many languages. To train PaLI, we make use of large pre-trained encoder-decoder language models and Vision Transformers (ViTs). This allows us to capitalize on their existing capabilities and leverage the substantial cost of training them. We find that joint scaling of the vision and language components is important. Since existing Transformers for language are much larger than their vision counterparts, we train a large, 4-billion parameter ViT (ViT-e) to quantify the benefits from even larger-capacity vision models. To train PaLI, we create a large multilingual mix of pretraining tasks, based on a new image-text training set containing 10B images and texts in over 100 languages. PaLI achieves state-of-the-art in multiple vision and language tasks (such as captioning, visual question-answering, scene-text understanding), while retaining a simple, modular, and scalable design.