🚀 Looking for a novel method to enhance classification robustness under real-world label noise?

Check out the work "An Embedding is Worth a Thousand Noisy Labels" led by @francescodisalvo.bsky.social & published in @tmlrorg.bsky.social.

📝 openreview.net/forum?id=X3g...
🐙 github.com/francescodis...

🚀 Looking for a comprehensive benchmark for the MedMNIST+ database?

Check out our latest paper, "Rethinking model prototyping through the MedMNIST+ dataset collection" now published open-access in #ScientificReports.

📝 nature.com/articles/s41...
🐙 github.com/sdoerrich97/...

If you are at #BMVC2024 in Glasgow 🏴󠁧󠁢󠁳󠁣󠁴󠁿 and interested in robust, automatic medical image diagnosis, feel free to drop by my oral tomorrow

🗓️ Wednesday, October 27, 2024
📍 M3
🕒 11 AM
🖼️ Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representations

📝: arxiv.org/abs/2409.12276