Nermin Samet

E-mail

snermin@metu.edu.tr

Department

Department of Computer Engineering

ORCID

0000-0001-9247-2504

Scopus Author ID

55420007200

Web of Science Researcher ID

ABA-3888-2020

HoughNet: Integrating Near and Long-Range Evidence for Visual Detection Samet, Nermin; Hicsonmez, Samet; Akbaş, Emre (2022-1-01) IEEEThis paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location ...
Adversarial segmentation loss for sketch colorization Hicsonmez, Samet; Samet, Nermin; Akbaş, Emre; DUYGULU ŞAHİN, PINAR (2021-01-01) 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” translation approach. We argue that segm...
Reducing Label Noise in Anchor-Free Object Detection Samet, Nermin; Hiçsönmez, Samet; Akbaş, Emre (2020-08-03)
GANILLA: Generative adversarial networks for image to illustration translation Hicsonmez, Samet; Samet, Nermin; Akbaş, Emre; DUYGULU ŞAHİN, PINAR (Elsevier BV, 2020-03-01) In this paper, we explore illustrations in children's books as a new domain in unpaired image-to-image translation. We show that although the current state-of-the-art image-to-image translation models successfully transfer...
Reducing Label Noise in Anchor-Free Object Detection Samet, Nermin; Hicsonmez, Samet; Akbaş, Emre (2020-01-01) Current anchor-free object detectors label all the features that spatially fall inside a predefined central region of a ground-truth box as positive. This approach causes label noise during training, since some of these po...
Who draw this? Caricaturist recognition using convolutional neural networks Bunu kim çizdi? Evrişimsel sinir aǧlari ile karikatürist tanima Hicsonmez, Samet; Samet, Nermin; Akbaş, Emre; Duygulu, Pinar (2018-05-05) Caricature is the art of expressing an event that will be described in many pages in writing, visually with a small drawing. The details of the drawing, the style, and the objects used in the drawing, which make up the vis...
Could we create a training set for image captioning using automatic translation? Görüntü Altyazilama için Otomatik Tercüeyle Eǧitim Kümesi Oluşturulabilir mi? Samet, Nermin; Duygulu, Pinar; Akbaş, Emre (2017-05-18) Automatic image captioning has received increasing attention in recent years. Although there are many English datasets developed for this problem, there is only one Turkish dataset and it is very small compared to its Engl...

Citation Formats