TULIP: Towards Unified Language-Image Pretraining

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Zineng, Lian, Long, Eisape, Seun, Wang, XuDong, Herzig, Roei, Yala, Adam, Suhr, Alane, Darrell, Trevor, Chan, David M.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908305857708032
author Tang, Zineng
Lian, Long
Eisape, Seun
Wang, XuDong
Herzig, Roei
Yala, Adam
Suhr, Alane
Darrell, Trevor
Chan, David M.
author_facet Tang, Zineng
Lian, Long
Eisape, Seun
Wang, XuDong
Herzig, Roei
Yala, Adam
Suhr, Alane
Darrell, Trevor
Chan, David M.
contents Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understanding, such as counting, depth estimation, and fine-grained object recognition. These models, by performing language alignment, tend to prioritize high-level semantics over visual understanding, weakening their image understanding. On the other hand, vision-focused models are great at processing visual information but struggle to understand language, limiting their flexibility for language-driven tasks. In this work, we introduce TULIP, an open-source, drop-in replacement for existing CLIP-like models. Our method leverages generative data augmentation, enhanced image-image and text-text contrastive learning, and image/text reconstruction regularization to learn fine-grained visual features while preserving global semantic alignment. Our approach, scaling to over 1B parameters, outperforms existing state-of-the-art (SOTA) models across multiple benchmarks, establishing a new SOTA zero-shot performance on ImageNet-1K, delivering up to a $2\times$ enhancement over SigLIP on RxRx1 in linear probing for few-shot classification, and improving vision-language models, achieving over $3\times$ higher scores than SigLIP on MMVP. Our code/checkpoints are available at https://tulip-berkeley.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2503_15485
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TULIP: Towards Unified Language-Image Pretraining
Tang, Zineng
Lian, Long
Eisape, Seun
Wang, XuDong
Herzig, Roei
Yala, Adam
Suhr, Alane
Darrell, Trevor
Chan, David M.
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understanding, such as counting, depth estimation, and fine-grained object recognition. These models, by performing language alignment, tend to prioritize high-level semantics over visual understanding, weakening their image understanding. On the other hand, vision-focused models are great at processing visual information but struggle to understand language, limiting their flexibility for language-driven tasks. In this work, we introduce TULIP, an open-source, drop-in replacement for existing CLIP-like models. Our method leverages generative data augmentation, enhanced image-image and text-text contrastive learning, and image/text reconstruction regularization to learn fine-grained visual features while preserving global semantic alignment. Our approach, scaling to over 1B parameters, outperforms existing state-of-the-art (SOTA) models across multiple benchmarks, establishing a new SOTA zero-shot performance on ImageNet-1K, delivering up to a $2\times$ enhancement over SigLIP on RxRx1 in linear probing for few-shot classification, and improving vision-language models, achieving over $3\times$ higher scores than SigLIP on MMVP. Our code/checkpoints are available at https://tulip-berkeley.github.io
title TULIP: Towards Unified Language-Image Pretraining
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2503.15485