Deep supervised conistrastive learning for small datasets (few shot learning). This repository takes labeled embedding data ,that could be extracted from pre-trained NLP, vision, or any other algorithm that extract embedding, and use deep FFN to learn new embedding that is fine-tuned for the current data. Th algorithm can improve classification per
Deep supervised (or semi-supervised) contrastive learning for small datasets (few shot learning). This repository takes labeled embedding data, that could be extracted from pre-trained NLP, vision, or any other algorithm that extract embedding, and use deep FFN to learn new embedding that is fine-tuned for your subset of classes and data. This algorithm can improve classification performance even for small amount of data-per class.
Deep supervised conistrastive learning for small datasets (few shot learning). This repository takes labeled embedding data ,that could be extracted from pre-trained NLP, vision, or any other algorithm that extract embedding, and use deep FFN to learn new embedding that is fine-tuned for the current data. Th algorithm can improve classification per