---
title: OpenPhenom
description: Channel-agnostic image encoding model CA-MAE with a ViT-S/16 encoder backbone designed for microscopy image featurization. The model uses a vision transformer backbone with channelwise cross-attention over patch tokens to create contextualized representations separately for each
tags:
- MAE
- custom_code
- feature-extraction
- imaging
- phenomics
source_url: https://huggingface.co/recursionpharma/OpenPhenom
---

# OpenPhenom

> **Mirrored metadata.** This card is reproduced on Atlas for discovery. The artifact itself is not hosted here — follow the source link for the files, and refer to the upstream licence for terms of use.

Channel-agnostic image encoding model CA-MAE with a ViT-S/16 encoder backbone designed for microscopy image featurization. The model uses a vision transformer backbone with channelwise cross-attention over patch tokens to create contextualized representations separately for each

Upstream identifier: `recursionpharma/OpenPhenom`.

**Source:** https://huggingface.co/recursionpharma/OpenPhenom

_This model is part of the Atlas demo catalogue. See the repository history for provenance._