6 papers
Deep Sprite-based Image Models: An Analysis
Zeynep Sonat Baltacı, Romain Loiseau, Mathieu Aubry
While foundation models drive steady progress in image segmentation and diffusion algorithms compose always more realistic images, the seemingly simple problem of identifying recur…
Text region detection in historical astronomical diagrams
Zeynep Sonat Baltacı, Raphaël Baena, Fei Meng +4
Text detection is a crucial task in the analysis of historical documents. While datasets and benchmarks exist for text detection in manuscripts and maps, the study of text in mathe…
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
David Picard, Nicolas Dufour, Lucas Degeorge +14
This paper introduces the Polynomial Mixer (PoM), a novel token mixing mechanism with linear complexity that serves as a drop-in replacement for self-attention. PoM aggregates inpu…
Intrinsic Dimensionality as a Model-Free Measure of Class Imbalance
ÃaÄrı Eser, Zeynep Sonat Baltacı, Emre AkbaÅ +1
Imbalance in classification tasks is commonly quantified by the cardinalities of examples across classes. This, however, disregards the presence of redundant examples and inherent…
Class Uncertainty: A Measure to Mitigate Class Imbalance
Z. S. Baltaci, K. Oksuz, S. Kuzucu +5
Class-wise characteristics of training examples affect the performance of deep classifiers. A well-studied example is when the number of training examples of classes follows a long…
Historical Printed Ornaments: Dataset and Tasks
Sayan Kumar Chaki, Zeynep Sonat Baltaci, Elliot Vincent +5
This paper aims to develop the study of historical printed ornaments with modern unsupervised computer vision. We highlight three complex tasks that are of critical interest to boo…