yuhui-zh15/C3
Official implementation of "Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data" (ICLR 2024)
This project helps AI researchers and practitioners build applications that process and generate different types of media, such as image to text, audio to text, or text to image. It takes existing pre-trained models and uni-modal data (like a collection of images without their descriptions) and produces models capable of understanding or generating content across modalities. This is ideal for those developing advanced AI systems in computer vision, natural language processing, and audio analysis who face challenges with acquiring paired multi-modal datasets.
No commits in the last 6 months.
Use this if you need to develop AI models that translate between different data types (like generating text from an image or an image from text) but only have access to large amounts of single-modality data.
Not ideal if you already have extensive paired multi-modal datasets or are working on tasks that don't involve translating between different media types.
Stars
34
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 16, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yuhui-zh15/C3"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification