Hybrid Discriminative-Generative Training via Contrastive Learning
-
Updated
May 1, 2023 - Python
Hybrid Discriminative-Generative Training via Contrastive Learning
[NeurIPS'25] A work to improve CLIP's visual detail capturing ability by inverting the unCLIP generative model.
Compilation of Natural Language Processing (NLP) codes. BONUS: Link to Information Retrieval (IR) codes compilation. (checkout the readme)
Build a predictive system, which will take different handwritten digit images as a path and can recognize the label of the image data using nueral network.
A work to explore discriminative abilities in frozen pretrained generative models.
Source code of the GemClus package
Add a description, image, and links to the discriminative-model topic page so that developers can more easily learn about it.
To associate your repository with the discriminative-model topic, visit your repo's landing page and select "manage topics."