At SP4CING, we aim at designing signal processing techniques for computational intelligence applications. Our research covers problems in diversified fields, ranging from environmental monitoring to multi-modal surveillance, from bio-image analysis to remote sensing. Check out our research page for more information and learn more about our latest papers.
Our paper titled "Averager Student: Distillation from Undistillable Teacher" is accepted by Tiny Papers @ ICLR 2023. In this paper, with the aim of contributing to solutions for model intellectual property (IP) protection, a novel approach is proposed, which improves the distillation from an undistillable teacher whose goal is make the distillation difficult for students, with the purpose of model protection.
We are pleased to announce the 8th Science Academy Machine Learning Summer School, which will be held in Suleyman Demirel Cultural Center in Istanbul Technical University between 22-25 June this year. Istanbul Technical University Informatics Institute organizes this summer school under the supervision of the Science Academy. Read more here.
The International Workshop on Computational Intelligence for Multimedia Understanding (IWCIM) is the annual workshop organized by the working group Multimedia Understanding through Semantics, Computation and Learning (MUSCLE) of the European Research Consortium for Informatics and Mathematics (ERCIM). This year, IWCIM takes place as a satellite workshop to IEEE ICASSP 2023, to be held in Rhodes Island, Greece on June 4 - 9, 2023. Read more here.
Reyhan Kevser Keser is the leading author of a recent paper on knowledge distillation titled as “PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation” which is available online in 'Expert Systems with Applications' journal. Read more here.
Onur Can Koyun is the leading author of a recent paper on small object detection titled as “Focus-and-Detect: A small object detection framework for aerial images” which has been published in 'Signal Processing: Image Communication' journal. Read more here.
The M.S. thesis, “Rotational Duplicate Layer: A New and Compact Convolutional Neural Network Layer” by Mr. Erdem Safa Akkul was chosen to be the best thesis in terms of thesis outcomes among all ASELSAN Akademi theses across all disciplines in 2022. Outcomes of Mr. Akkul’s thesis work include two international conference papers and one national patent disclosure. Mr. Akkul’s thesis was supervised by Prof. Behçet Uğur Töreyin.