Shypd.aiThe largest open index of AI toolsIIC (Invariant Information Clustering) is an open-source AI tool that trains neural networks for unsupervised image classification and segmentation. It achieves state-of-the-art semantic accuracy without requiring labels.
Trending
About
IIC (Invariant Information Clustering) provides PyTorch code for an unsupervised clustering objective designed to train neural networks for image classification and segmentation. This tool allows users to achieve state-of-the-art semantic accuracy without the need for labeled data. It has set new records on various datasets including STL10, CIFAR10, MNIST, and COCO-Stuff. Users can integrate the IIC loss function into their own code or modify existing scripts within the codebase. A key recommendation for improved performance is the implementation of auxiliary overclustering. The repository also provides resources for downloading trained models, setting up segmentation datasets, and includes links to various forks, including TensorFlow implementations.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
