Kemal Öksüz bio photo

Kemal Öksüz

I'm from a seaside town near Balıkesir, Turkey. Currently in Riga, Latvia. Passionate about computer vision.

Twitter   G. Scholar LinkedIn Github e-Mail

Me in a Nutshell

I have received my B.Sc. degree from the Land Forces Academy of Turkey in 2008 and M.Sc. in 2016 from Dept. of Computer Engineering, Bogazici University under the supervision of Assoc. Prof. Ali Taylan Cemgil. I have received my Ph.D. degree in 2021 from Dept. of Computer Engineering, Middle East Technical University (METU) under the supervision of Assoc. Prof. Sinan Kalkan and Asst. Prof. Emre Akbaş. Currently, I am working for Turkish Armed Forces. I am also a research associate at Image Lab, METU. My research interests include computer vision with a focus on visual detection (including segmentation), imbalance problems and non-differerentiable optimization (essentially problems involving ranking).

Recent News

July 2021 - Our paper, Rank & Sort Loss for Object Detection and Instance Segmentation, has been accepted to ICCV 2021 for oral presentation. The code is available in our project page.
May 2021 - I have successfully defended my PhD Thesis titled Identifying and Addressing Imbalance Problems in Visual Detection. It will be public in short.
December 2020 - I gave a talk (in Turkish) about aLRP Loss in NeurIPS Meetup Turkey. You can check out the talk and slides.
November 2020 - Our new preprint, One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks , is online! This paper extends the LRP Error, previosly published in ECCV 2018, to all visual detection tasks. You can find the implementation of LRP Error on commonly used datasets (COCO, LVIS and Panoptic-COCO) in our project page.
September 2020 - Our paper, A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection, has been accepted to NeurIPS 2020 as a spotlight. The code is available in our project page.
August 2020 - In our Workshop on Imbalance Problems on Computer Vision, ECCV 2020, I gave a talk on Imbalance Problems in Object Detection including problem definitions, common methods and current trends. You can watch my talk, other invited talks and paper presentations from our workshop YouTube channel.
March 2020 - Our paper, Imbalance Problems in Object Detection: A Review, has been accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). See our project page.
February 2020 - We are organizing Imbalance Problems in Computer Vision (IJCV) workshop in ECCV 2020. For further information, please check the workshop page.
December 2019 - Our paper, Generating Positive Bounding Boxes for Balanced Training of Object Detectors is accepted to Winter Conference on Applications of Computer Vision (WACV), 2020. See our project page.