Do Vision and Language Models Share Concepts? A Vector Space Alignment Study

In this work (Li et al., 2024), we have studied the question of whether LMs and VMs learn similar representations of the world, despite being trained on independent data from independent modalities. We present an empirical evaluation across four families of LMs (BERT, GPT-2, OPT, and LLaMA-2) and three vision model architectures (ResNet, Segformer, and MAE). Our experiments show that LMs partially converge towards representations isomorphic to those of VMs.

Getting Started

You can clone this repository issuing:

git clone git@github.com:jiaangli/VLCA.git
cd VLCA
git submodule update --init MUSE

1. Create a fresh conda environment and install all dependencies.

conda create -n vlca python=3.11
conda activate vlca
pip install -r requirements.txt

2. Datasets As part of this work, we release the following datasets:

Dataset	Dataset HF Alias
Common Words 79K	`jaagli/common-words-79k`
IMAGENET with Unique Labels (coming soon)	`jaagli/imagenet-ul`
English CLDI (coming soon)	`jaagli/en-cldi`

How to run

Check available model configurations in config.py under MODEL_CONFIGS, available saving paths of datasets under DataConfig, runtime parameters under MuseConfig, and various experimental types under ExperimentType.

Set the corresponding paths in all the files in conf folder.

Example to sequentially run GPT2 and OPT-125m models on ImageNet-21K dataset:

python main.py \
    --multirun \
    +model=gpt2,opt-125m \
    +dataset=imagenet \
    muse.exp_type=BASE

Or only run GPT-2 model on EN-CLDI dataset:

python main.py \
    +model=gpt2 \
    +dataset=cldi \
    muse.exp_type=BASE

Findings

LMs converge toward the geometry of visual models as they grow larger.

We also investigate the effects of incorporating text signals during vision pretraining by comparing pure vision models against selected CLIP vision encoders.

Citation

If you find our code, data or ideas useful in your research, please consider citing the paper:

@misc{li2024visionlanguagemodelsshare,
      title={Do Vision and Language Models Share Concepts? A Vector Space Alignment Study}, 
      author={Jiaang Li and Yova Kementchedjhieva and Constanza Fierro and Anders Søgaard},
      year={2024},
      eprint={2302.06555},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2302.06555}, 
}

Acknowledgement

Our codebase heavily relies on these excellent repositories:

jiaangli / VLCA