Papers
arxiv:2305.16999

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

Published on May 26, 2023
· Submitted by akhaliq on May 29, 2023
Authors:
,
,
,
,
,
,

Abstract

We introduce Three Towers (3T), a flexible method to improve the contrastive learning of vision-language models by incorporating pretrained image classifiers. While contrastive models are usually trained from scratch, LiT (Zhai et al., 2022) has recently shown performance gains from using pretrained classifier embeddings. However, LiT directly replaces the image tower with the frozen embeddings, excluding any potential benefits of contrastively training the image tower. With 3T, we propose a more flexible strategy that allows the image tower to benefit from both pretrained embeddings and contrastive training. To achieve this, we introduce a third tower that contains the frozen pretrained embeddings, and we encourage alignment between this third tower and the main image-text towers. Empirically, 3T consistently improves over LiT and the CLIP-style from-scratch baseline for retrieval tasks. For classification, 3T reliably improves over the from-scratch baseline, and while it underperforms relative to LiT for JFT-pretrained models, it outperforms LiT for ImageNet-21k and Places365 pretraining.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2305.16999 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2305.16999 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2305.16999 in a Space README.md to link it from this page.

Collections including this paper 1