2 papers
cs.CV2025
Glioma C6: A Novel Dataset for Training and Benchmarking Cell Segmentation
Roman Malashin, Svetlana Pashkevich, Daniil Ilyukhin +4
We present Glioma C6, a new open dataset for instance segmentation of glioma C6 cells, designed as both a benchmark and a training resource for deep learning models. The dataset co…
cs.AI2025
Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy
Roman Malashin, Valeria Yachnaya, Alexander Mullin
We investigate the training dynamics of deep classifiers by examining how hierarchical relationships between classes evolve during training. Through extensive experiments, we argue…