← Search

Antonin Vobecky

2 accepted papers

2025

DIP: Unsupervised Dense In-Context Post-training of Visual Representations

ICCV 2025poster

We introduce DIP, a novel unsupervised post-training method designed to enhance dense representations in large-scale pretrained vision encoders for in-context scene understanding. Unlike prior approaches using complex self-distillation architectures, our method trains the vision encoder using pseudo…

2022

Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation

ECCV 2022poster

"This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city. Our contributions are threefold. First, we propose a novel…