iiinova — where your digital self keeps evolving

Reposted by Pavel Suma

Bill Psomas @billpsomas.bsky.social · 24/04/2026

🇧🇷 Presenting our ICLR 2026 paper “Efficient Probing” (EP) today! ❓What if linear probing is asking the wrong question? 🥳 EP is a lightweight attention probing method that better evaluates local, patch-level representations from models like MIM. 📍Friday 24 April, P4-#3713, 15:15–17:45

0157

Pavel Suma @psuma.bsky.social · 23/04/2026

🚨 Efficient Local Visual Similarity (ELViS) @ #ICLR 2026 🇧🇷 ELViS is a fast, lightweight, and interpretable module for estimating image-to-image similarity that generalizes well to many image domains. Paper: arxiv.org/abs/2603.28603 Code: github.com/pavelsuma/ELViS Come see poster today @ P4-#3715

1147

Reposted by Pavel Suma

Giorgos Kordopatis-Zilos @gkordo.bsky.social · 05/09/2025

🚀 new state-of-the-art on ILIAS dataset! Curious how well the latest models can recognize particular objects? We evaluated the base and large variants of DINOv3 and Perception Encoder (PE) on instance-level image retrieval. See the results 👉 vrg.fel.cvut.cz/ilias/

1135

Reposted by Pavel Suma

Giorgos Kordopatis-Zilos @gkordo.bsky.social · 27/02/2025

ILIAS is a large-scale test dataset for evaluation on Instance-Level Image retrieval At Scale. It is designed to support future research in image-to-image and text-to-image retrieval for particular objects and serves as a benchmark for evaluating foundation models and retrieval techniques.

23915

Reposted by Pavel Suma

Giorgos Tolias @gtolias.bsky.social · 12/02/2025

For PhD and MSc students interested in a research visit to Prague/VRG in 2025: we're open to hosting short-term collaborations or internships on a range of computer vision topics. If this sounds exciting, reach out by e-mail! We'd love to discuss potential projects. Some examples 🧵 #Internship #CV

12722

Reposted by Pavel Suma

Giorgos Tolias @gtolias.bsky.social · 20/11/2024

Deep global descriptors give a convenient way for retrieval, but local descriptors are a game changer in finding needles in a haystack (particular objects in clutter). Due to their high cost, with AMES we optimize the performance/memory trade-off during re-ranking. #ECCV2024

1328