metadata

license: apache-2.0

Model Details

Perception Encoder (PE) is a state-of-the-art encoder for image and video understanding trained via simple vision-language learning. It was introduced in "Perception Encoder: The best visual embeddings are hidden inside the network".

Model Developer: Meta

Model Overview: Perception Encoder (PE) is a family of large-scale vision encoder models with state-of-the-art performance on a large variety of vision tasks. By using a robust contrastive pretraining recipe and finetuning on synthetically aligned videos, PE not only outperforms all existing models on classification and retrieval, but it also internally produces strong, general features that scale for downstream tasks. PE unlocks the ability for large-scale contrastive pretraining to transfer to downstream tasks with alignment tuning to capitalize on those general features.

Scale	Tower	Params	Width	Depth	MLP	Heads	CLIP Dim	Resolution	Patch Size	Text Context Length
B	Vision	0.09B	768	12	3072	12	1024	384	16	32
	Text	0.31B	1024	24	4096	16	1024	384	16	32
L	Vision	0.32B	1024	24	4096	16	1024	336	14	32
	Text	0.31B	1024	24	4096	16	1024	336	14	32
G	Vision	1.88B	1536	50	8960	16	1280	392	14	72
	Text	0.47B	1280	24	5120	20	1280	392	14	72

How to use

PE codebase

We provide the pretraining code in https://github.com/meta-ai-research-fair/occhi.git

You can find more details in the GitHub repo.

Evaluation

We evaluate the pretrained MobileLLM models on Zero-shot Common Sense Reasoning tasks

Here is the table in Markdown format:

Zero-Shot Image Results

Zero-Shot Video Results

Citation

If you find our code useful for your research, please consider citing:

@article{PE,
    title={Perception Encoder},
    author={},
    journal={arXiv:xxx.xxxxx},
    year={2025}
}