Vladan Stojnić

I am a PhD student at the Visual Recognition Group, Czech Technical University in Prague. My PhD advisor is Giorgos Tolias.

I have a BSc and MSc in Electrical Engineering (focus on Computer Science) from the Faculty of Electrical Engineering, University of Banja Luka, where I was also a teaching and research assistant from 2018 to 2021.

Email  /  CV  /  Scholar /  Twitter /  GitHub  /  LinkedIn

Research

I'm interested in learning with limited supervision, specifically with the application to visual recognition.

LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation

This work introduces LPOSS, a training-free method for open-vocabulary semantic segmentation using Vision-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs through label propagation, which jointly optimizes predictions by incorporating patch-to-patch relationships. We address resolution limitations inherent to patch-based encoders by applying label propagation at the pixel level as a refinement step, significantly improving segmentation accuracy near class boundaries.

ILIAS: Instance-Level Image retrieval At Scale

This work introduces ILIAS, a new test dataset for Instance-Level Image retrieval At Scale. It is designed to evaluate the ability of current and future foundation models and retrieval techniques to recognize particular objects.

Label Propagation for Zero-shot Classification with Vision-Language Models

We tailor label propagation to VLMs and zero-shot classification over bi-modal graphs, and propose an efficient way for performing inductive inference with label propagation via a dual solution and through sparsification.

Training Ensembles With Inliers and Outliers for Semi-Supervised Active Learning

We show that simple ingredients such as joint training with inliers and outliers, semi-supervision, and ensembles enable classical active learning methods to achieve state-of-the-art results in the presence of outliers.

Research before PhD

During my master's studies, I was doing research focused mainly on remote sensing applications.

Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Coding

We conduct an extensive analysis of the applicability of self-supervised learning in remote sensing image classification and show that self-supervised learning can be easily extended to multispectral images.

A Method for Detection of Small Moving Objects in UAV Videos

We develop a method trained on synthetic data for the detection of tiny moving objects (bees) in the video.

Design and source code from Jon Barron's website