Digital Signal Processing and Image Analysis (DSB) 's Avatar

Digital Signal Processing and Image Analysis (DSB)

@dsb-uio.bsky.social

We are the DSB group at the Department of Informatics (IFI) at University of Oslo https://www.mn.uio.no/ifi/english/research/groups/dsb/

12 Followers  |  10 Following  |  2 Posts  |  Joined: 18.02.2025  |  1.393

Latest posts by dsb-uio.bsky.social on Bluesky

Post image

Come to our poster @icmlconf.bsky.social (Thu 17, morning) to discover more about it

Or check our paper: sthalles.github.io/sop/

09.07.2025 19:09 β€” πŸ‘ 1    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0
Video thumbnail

Self-Organizing Visual Prototypes (SOP) is a new, non-parametric approach to SSL that addresses these issues by representing each region in feature space using multiple real data embeddings (support embeddings), rather than a single learnable prototype.

09.07.2025 19:09 β€” πŸ‘ 1    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0
Post image

SSL, in particular, CL, relies more and more on prototypes (learnable representations that hold some group meaning)

But! overclustering, enforcing equipartitions, and underrepresentation are still problems that plague the prototypes

We solve them with our method: SOP

09.07.2025 19:09 β€” πŸ‘ 2    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0
Post image

Journal discussion Tuesday!

18.02.2025 14:58 β€” πŸ‘ 1    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0

Hello world!

18.02.2025 10:59 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Equivariant Self-Supervision: Exploiting Inductive Biases of Capsule Networks: Aiden Durrant
YouTube video by SFI Visual Intelligence Equivariant Self-Supervision: Exploiting Inductive Biases of Capsule Networks: Aiden Durrant

Did you miss out on the latest Visual Intelligence Online Seminar on equivariant self-supervision by Aiden Durrant? πŸ‘¨β€πŸ« πŸ€– 🧠

πŸ“Ί You can watch Durrant's talk on the Visual Intelligence YouTube channel: youtu.be/bsUGgwDYdXQ?...

14.02.2025 13:12 β€” πŸ‘ 2    πŸ” 2    πŸ’¬ 0    πŸ“Œ 0

@dsb-uio is following 10 prominent accounts