Vladan Stojnić

1/n #CVPR2026 Accepted Paper🚀 𝑨𝒓𝒆 𝒂 𝑭𝒆𝒘 𝑬𝒙𝒂𝒎𝒑𝒍𝒆𝒔 𝑬𝒏𝒐𝒖𝒈𝒉 𝒕𝒐 𝑩𝒓𝒊𝒅𝒈𝒆 𝒕𝒉𝒆 𝑺𝒖𝒑𝒆𝒓𝒗𝒊𝒔𝒊𝒐𝒏 𝑮𝒂𝒑 𝒊𝒏 𝑶𝒑𝒆𝒏-𝑽𝒐𝒄𝒂𝒃𝒖𝒍𝒂𝒓𝒚 𝑺𝒆𝒈𝒎𝒆𝒏𝒕𝒂𝒕𝒊𝒐𝒏? 𝑹𝒆𝒕𝒓𝒊𝒆𝒗𝒆 𝒂𝒏𝒅 𝑺𝒆𝒈𝒎𝒆𝒏𝒕 (𝑹𝑵𝑺) answers this question. Paper/code👇🏼

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation? Tilemachos Aravanis @stojnvla @bill_psomas Nikos Komodakis, Giorgos Tolias tl;dr: almost yes if use 1-3 images, no if more (fig 6) arxiv.org/abs/2602.23339 #CVPR2026

🚀 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/

Many thanks to the amazing collaborators: @ryan_c_ramos , @g_kordo , Yuta Nakashima, Giorgos Tolias , @noagarciad

If this caught your attention, check out our new paper. Processing and acquisition traces in visual encoders: What does CLIP know about your camera? arxiv.org/abs/2508.10637 To be presented at #ICCV2025 (highlight). @ICCVConference

Have you ever asked yourself how much your favorite vision model knows about image capture parameters (e.g., the amount of JPEG compression, the camera model, etc.)? Furthermore, could these parameters influence its semantic recognition abilities?

One of the biggest bottlenecks in deploying visual AI and computer vision is annotation, which can be both costly and time-consuming. Today, we’re introducing Verified Auto Labeling, a new approach to AI-assisted annotation that achieves up to 95% of human-level performance while cutting labeling costs by up to 100,000x and time by 5,000x. Read the full paper: arxiv.org/abs/2506.02359

🚨 Call for Papers! 7th Instance-Level Recognition and Generation Workshop (ILR+G) at @ICCVConference 📍 Honolulu, Hawaii 🌺 📅 October 19–20, 2025 🌐 ilr-workshop.github.io/ICCVW2025/ in-proceedings deadline: June 7 out-of-proceedings deadline: June 30 #ICCV2025

@g_kordo @huggingface @vanstriendaniel also @NielsRogge for the inital contact about hosting on @huggingface

@g_kordo @huggingface Thanks @vanstriendaniel for the help with hosting on @huggingface

Exciting News! Shoutout to @huggingface🤗 for hosting ILIAS in its full scale! You can now easily download it via: huggingface.co/datasets/vrg-p… This is a milestone in i2i and t2i retrieval, paving the way for significant advancements. Huge thanks to HF team for their support!

To be presented at #CVPR2025. Work done with Yannis Kalantidis, Jiri Matas, and Giorgos Tolias

Be sure to check out the demo on @huggingface spaces and play with it.🙂 huggingface.co/spaces/stojnvl…

We are happy to share LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation. LPOSS is a training-free method for open-vocabulary semantic segmentation using Vision-Language Models.