Focus-and-Detect: A Small Object Detection Framework for Aerial Images

no code implementations • 24 Mar 2022 • Onur Can Koyun, Reyhan Kevser Keser, İbrahim Batuhan Akkaya, Behçet Uğur Töreyin

Despite recent advances, object detection in aerial images is still a challenging task.

Object object-detection +2

ResVGAE: Going Deeper with Residual Modules for Link Prediction

no code implementations • 3 May 2021 • Indrit Nallbani, Reyhan Kevser Keser, Aydin Ayanzadeh, Nurullah Çalık, Behçet Uğur Töreyin

We show that our multiple residual modules, a convolutional layer with residual connection, improve the average precision of the graph autoencoders.

Link Prediction Representation Learning

PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation

no code implementations • 26 Feb 2021 • Reyhan Kevser Keser, Aydin Ayanzadeh, Omid Abdollahi Aghdam, Caglar Kilcioglu, Behcet Ugur Toreyin, Nazim Kemal Ure

One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model.

Clustering Knowledge Distillation +1