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× enhancement over SigLIP on RxRx1 in linear probing for few-shot classification, and improving vision-language models, achieving over 3× higher scores than SigLIP on MMVP. Our code/checkpoints are available at https://tulip-berkeley.github.io
@article{arxiv.2503.15485,
title = {TULIP: Towards Unified Language-Image Pretraining},
author = {Zineng Tang and Long Lian and Seun Eisape and XuDong Wang and Roei Herzig and Adam Yala and Alane Suhr and Trevor Darrell and David M. Chan},
journal= {arXiv preprint arXiv:2503.15485},
year = {2025}
}