insitro/ContextViT
Contextual Vision Transformers for Robust Representation Learning
This project helps biological researchers and drug discovery scientists interpret complex microscopy images more accurately. It takes in sets of cell images, grouped by experimental conditions or plates, and outputs robust image representations. This allows for more reliable analysis, especially when dealing with new, unseen experimental conditions or variations in data.
No commits in the last 6 months.
Use this if you need to extract reliable, context-aware features from high-dimensional image data, particularly from biological assays like cell painting, even when experimental conditions vary or new conditions are introduced.
Not ideal if your image data is simple, does not involve distinct contextual groups, or if you are not working with out-of-distribution generalization challenges.
Stars
15
Forks
2
Language
Python
License
—
Category
Last pushed
Oct 19, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/insitro/ContextViT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...