Papers
arxiv:2310.09199

PaLI-3 Vision Language Models: Smaller, Faster, Stronger

Published on Oct 13, 2023
Β· Submitted by akhaliq on Oct 16, 2023
#2 Paper of the day
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

This paper presents PaLI-3, a smaller, faster, and stronger vision language model (VLM) that compares favorably to similar models that are 10x larger. As part of arriving at this strong performance, we compare Vision Transformer (ViT) models pretrained using classification objectives to contrastively (SigLIP) pretrained ones. We find that, while slightly underperforming on standard image classification benchmarks, SigLIP-based PaLI shows superior performance across various multimodal benchmarks, especially on localization and visually-situated text understanding. We scale the SigLIP image encoder up to 2 billion parameters, and achieves a new state-of-the-art on multilingual cross-modal retrieval. We hope that PaLI-3, at only 5B parameters, rekindles research on fundamental pieces of complex VLMs, and could fuel a new generation of scaled-up models.

Community

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

PaLI-3: Unveiling the Power of Compact and Efficient Vision Language Models

πŸ‘‰ Subscribe: https://www.youtube.com/@Arxflix
πŸ‘‰ Twitter: https://x.com/arxflix
πŸ‘‰ LMNT (Partner): https://lmnt.com/

By Arxflix
9t4iCUHx_400x400-1.jpg

Sign up or log in to comment

Models citing this paper 120

Browse 120 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2310.09199 in a dataset README.md to link it from this page.

Spaces citing this paper 20

Collections including this paper 11