Zeynep Sonat Baltacı

Historical Printed Ornaments: Dataset and Tasks

S. K. Chaki*, Z. S. Baltacı*, E. Vincent, R. Emonet, F. Vial-Bonacci, C. Bahier-Porte, M. Aubry, T. Fournel

[webpage], [ArXiv], [GitHub], [Poster], ICDAR 2024

We propose a historical printed ornament dataset associated with three different tasks: clustering, element discovery and unsupervised change localization.

Computer Vision and Historical Scientific Illustrations

F. Aouinti, Z. S. Baltacı, M. Aubry, A. Guilbaud, S. Lazaris

[webpage], [HAL], [GitHub], IAMAHA 2023

We present a semi-automatic interactive pipeline for scientific illustration extraction and introduce a new dataset of scientific illustrations.

Generalized Mask-aware IoU for Anchor Assignment for Real-time Instance Segmentation

K. Öksüz, B. C. Çam, F. Kahraman, Z. S. Baltacı, S. Kalkan, E. Akbaş

[arXiv], ArXiv

We propose Generalized Mask-aware IoUas a new measure for positive-negative assignment of anchor boxes during training of instance segmentation methods.

Class Uncertainty: A Measure to Mitigate Class Imbalance

Z. S. Baltacı, K. Öksüz, S. Kuzucu, K. Tezören, B. K. Konar, A. Özkan, E. Akbaş, S. Kalkan

[arXiv], Under Review

To measure class imbalance, we propose "Class Uncertainty" as the average predictive uncertainty of the training examples, and we show that this novel measure captures the differences across classes better than cardinality. We also curate SVCI-20 as a novel dataset in which the classes have equal number of training examples but they differ in terms of their hardness.

Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation

K. Öksüz, B. C. Çam, F. Kahraman, Z. S. Baltacı, S. Kalkan, E. Akbaş

[arXiv], [GitHub], BMVC 2021

We propose Mask-aware IoU, an IoU variant for better anchor assignment to supervise instance segmentation methods.