Multi-granularity Correspondence Learning from Long-term Noisy Videos [ICLR 2024, Oral]
-
Updated
Apr 18, 2024 - Python
Multi-granularity Correspondence Learning from Long-term Noisy Videos [ICLR 2024, Oral]
This is a summary of research on noisy correspondence. There may be omissions. If anything is missing please get in touch with us. Our emails: [email protected] [email protected] [email protected]
This repo contains the code and data of "Graph Matching with Bi-level Noisy Correspondence".
Noise of Web (NoW) is a challenging noisy correspondence learning (NCL) benchmark containing 100K image-text pairs for robust image-text matching/retrieval models.
Add a description, image, and links to the noisy-correspondence topic page so that developers can more easily learn about it.
To associate your repository with the noisy-correspondence topic, visit your repo's landing page and select "manage topics."