17 citations · 29 across the 13 of their papers we have counts for
4 papers · 1 filter
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…
TrickVOS: A Bag of Tricks for Video Object Segmentation
Evangelos Skartados, Konstantinos Georgiadis, Mehmet Kerim Yucel +5
Space-time memory (STM) network methods have been dominant in semi-supervised video object segmentation (SVOS) due to their remarkable performance. In this work, we identify three…
LP-IOANet: Efficient High Resolution Document Shadow Removal
Konstantinos Georgiadis, M. Kerim Yucel, Evangelos Skartados +4
Document shadow removal is an integral task in document enhancement pipelines, as it improves visibility, readability and thus the overall quality. Assuming that the majority of pr…
MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation
Roy Miles, Mehmet Kerim Yucel, Bruno Manganelli +1
This paper tackles the problem of semi-supervised video object segmentation on resource-constrained devices, such as mobile phones. We formulate this problem as a distillation task…