17 citations · 18 across the 5 of their papers we have counts for
6 papers
HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
Convolutional Neural Networks (CNN) are known to exhibit poor generalization performance under distribution shifts. Their generalization have been studied extensively, and one line…
Improving Sketch Colorization using Adversarial Segmentation Consistency
Samet Hicsonmez, Nermin Samet, Emre Akbas +1
We propose a new method for producing color images from sketches. Current solutions in sketch colorization either necessitate additional user instruction or are restricted to the "…
How Robust are Discriminatively Trained Zero-Shot Learning Models?
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
Data shift robustness has been primarily investigated from a fully supervised perspective, and robustness of zero-shot learning (ZSL) models have been largely neglected. In this pa…
Adversarial Segmentation Loss for Sketch Colorization
Samet Hicsonmez, Nermin Samet, Emre Akbas +1
We introduce a new method for generating color images from sketches or edge maps. Current methods either require some form of additional user-guidance or are limited to the "paired…
Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos
Yunus Can Bilge, Mehmet Kerim Yucel, Ramazan Gokberk Cinbis +2
In many real-world problems, there is typically a large discrepancy between the characteristics of data used in training versus deployment. A prime example is the analysis of aggre…
Rectifying Self Organizing Maps for Automatic Concept Learning from Web Images
Eren Golge, Pinar Duygulu
We attack the problem of learning concepts automatically from noisy web image search results. Going beyond low level attributes, such as colour and texture, we explore weakly-label…