iiinova — where your digital self keeps evolving

Illia Volkov 🇺🇦 🐈‍⬛

@c1rcuslegend.bsky.social

15 followers 47 following 2 posts

Posts Replies Media

Reposted by Illia Volkov 🇺🇦 🐈‍⬛

Kosta Derpanis @csprofkgd.bsky.social · 08/09/2026

Introducing our new #computervision influencer.

0163

Reposted by Illia Volkov 🇺🇦 🐈‍⬛

Klara Janouskova @klara-cz.bsky.social · 03/09/2026

🐕 🍄 🎻 🚜 ReImageNet is out. 🚜 🎻🍄� We reannotated the whole ImageNet-1k val set from scratch: 50,000 images, multilabel, 96,051 bounding boxes, new definitions for all 1,000 classes, five semantic attributes. Browse every annotation: vrg.fel.cvut.cz/reimagenet Paper: arxiv.org/abs/2608.13783

2218

Reposted by Illia Volkov 🇺🇦 🐈‍⬛

Giorgos Tolias @gtolias.bsky.social · 25/08/2026

Your camera leaves fingerprints on every photo. Vision encoders learned to read them. Read about the bad and the good sides of it. "Invisible Shortcuts: Why Vision Encoders Know Your Camera" has been accepted at ECCV 2026. Paper: arxiv.org/pdf/2608.05424 @eccv.bsky.social #ECCV2026

52712

Reposted by Illia Volkov 🇺🇦 🐈‍⬛

Klara Janouskova @klara-cz.bsky.social · 21/08/2026

Yaaay, the biggest "side project" of my phd is out! More posts coming soon :) In the meanwhile, you can have a look at the result via our preview vrg.fel.cvut.cz/reimagenet - it also serves as a tool to report issues after login.

vrg.fel.cvut.cz

ReImageNet

052

Reposted by Illia Volkov 🇺🇦 🐈‍⬛

Dmytro Mishkin @ducha-aiki.bsky.social · 21/08/2026

Doomed to Re-Annotate, Forever: The ImageNet Story Illia Volkov, Nikita Kisel, Tetiana Mishkina, @klara-cz.bsky.social Jiri Matas tl;dr: ImageNet val annotation with all bboxes, careful study of concepts, attributes (is drawing of a cat, a cat?) Year of efforts. 1/ arxiv.org/abs/2608.13783

1195

Reposted by Illia Volkov 🇺🇦 🐈‍⬛

Klara Janouskova @klara-cz.bsky.social · 07/08/2026

We needed region annotations. We looked at what already existed… and we decided to build our own dataset. Meet STRAP 🎉 🤗 huggingface.co/datasets/vrg-prague/STRAP 🔗 klarajanouskova.github.io/STRAP Region–text annotations for 2M web images, from a single pass of a frozen open MLLM. 🧵

165

Illia Volkov 🇺🇦 🐈‍⬛ @c1rcuslegend.bsky.social · 13/06/2026

peak music, flawless performance ＼⁠(⁠^⁠o⁠^⁠)⁠／

030

Reposted by Illia Volkov 🇺🇦 🐈‍⬛

Bill Psomas @billpsomas.bsky.social · 06/06/2026

🚨 Presenting today at #CVPR2026! Our highlight ⭐ paper Retrieve and Segment (RNS) asks a simple question: Can a few examples bridge the supervision gap in open-vocabulary segmentation? ✅ Turns out they can. 📍 Poster #578 ⏰ 16:45–18:45 📄 arxiv.org/abs/2602.23339

0103

Reposted by Illia Volkov 🇺🇦 🐈‍⬛

Klara Janouskova @klara-cz.bsky.social · 03/06/2026

📍 @c1rcuslegend.bsky.social is presenting our work at #CVPR2026 Findings, find the poster with the most 🐈🐾 🗓 Friday, 07:00–08:30 📌 ExHall A; Poster #166 Stop by if you're curious whether MLLMs make good classifiers or to discuss our "Doomed to Reannotate" ImageNet project (preprint coming soon) 📝

042

Reposted by Illia Volkov 🇺🇦 🐈‍⬛

Klara Janouskova @klara-cz.bsky.social · 09/03/2026

To study this, we introduce ReGT, a new multilabel reannotation of 625 ImageNet classes that corrects many of these issues. When evaluated on the cleaned labels, multimodal LLMs improve by up to +10.8% accuracy, substantially narrowing the gap with supervised vision models. 📈

143