2 code implementations • 5 Apr 2024 • Vladan Stojnić, Yannis Kalantidis, Giorgos Tolias
We leverage the graph structure of the unlabeled data and introduce ZLaP, a method based on label propagation (LP) that utilizes geodesic distances for classification.
1 code implementation • 7 Jul 2023 • Vladan Stojnić, Zakaria Laskar, Giorgos Tolias
In this work, we present an approach that leverages three highly synergistic components, which are identified as key ingredients: joint classifier training with inliers and outliers, semi-supervised learning through pseudo-labeling, and model ensembling.
1 code implementation • 5 Nov 2021 • Vladimir Risojević, Vladan Stojnić
Recently, the availability of larger high resolution remote sensing (HRRS) image datasets and progress in self-supervised learning have brought up the questions of whether supervised ImageNet pre-training is still necessary for remote sensing scene classification and would supervised pre-training on HRRS image datasets or self-supervised pre-training on ImageNet achieve better results on target remote sensing scene classification tasks.
Ranked #1 on Multi-Label Classification on MLRSNet
1 code implementation • 14 Apr 2021 • Vladan Stojnić, Vladimir Risojević
We show that, for the downstream task of remote sensing image classification, using self-supervised pre-training on remote sensing images can give better results than using supervised pre-training on images of natural scenes.
1 code implementation • 11 Feb 2021 • Vladan Stojnić, Vladimir Risojević, Mario Muštra, Vedran Jovanović, Janja Filipi, Nikola Kezić, and Zdenka Babić
To circumvent this problem, we propose training a CNN using synthetic videos generated by adding small blob-like objects to video sequences with real-world backgrounds.
Ranked #1 on Small Object Detection on Bee4Exp Honeybee Detection (using extra training data)