Digital Signal Processing and Image Analysis (DSB)
banner
dsb-uio.bsky.social
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/
Reposted by Digital Signal Processing and Image Analysis (DSB)
Come to our poster @icmlconf.bsky.social (Thu 17, morning) to discover more about it

Or check our paper: sthalles.github.io/sop/
July 9, 2025 at 7:10 PM
Reposted by Digital Signal Processing and Image Analysis (DSB)
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.
July 9, 2025 at 7:10 PM
Reposted by Digital Signal Processing and Image Analysis (DSB)
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
July 9, 2025 at 7:10 PM
Journal discussion Tuesday!
February 18, 2025 at 2:58 PM
Hello world!
February 18, 2025 at 10:59 AM
Reposted by Digital Signal Processing and Image Analysis (DSB)
Did you miss out on the latest Visual Intelligence Online Seminar on equivariant self-supervision by Aiden Durrant? 👨‍🏫 🤖 🧠

📺 You can watch Durrant's talk on the Visual Intelligence YouTube channel: youtu.be/bsUGgwDYdXQ?...
Equivariant Self-Supervision: Exploiting Inductive Biases of Capsule Networks: Aiden Durrant
YouTube video by SFI Visual Intelligence
youtu.be
February 14, 2025 at 1:12 PM