Kemal Oksuz

According to our database, Kemal Oksuz authored at least 19 papers between 2016 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

What Makes and Breaks Safety Fine-tuning? A Mechanistic Study.

Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip H. S. Torr, Amartya Sanyal, Puneet K. Dokania

CoRR, 2024

Bucketed Ranking-Based Losses for Efficient Training of Object Detectors.

Feyza Yavuz, Baris Can Cam, Adnan Harun Dogan, Kemal Oksuz, Emre Akbas, Sinan Kalkan

Proceedings of the Computer Vision - ECCV 2024, 2024

On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines.

Selim Kuzucu, Kemal Oksuz, Jonathan Sadeghi, Puneet K. Dokania

Proceedings of the Computer Vision - ECCV 2024, 2024

2023

Generalized Mask-aware IoU for Anchor Assignment for Real-time Instance Segmentation.

Baris Can Çam, Kemal Öksüz, Fehmi Kahraman, Zeynep Sonat Baltaci, Sinan Kalkan, Emre Akbas

CoRR, 2023

Class Uncertainty: A Measure to Mitigate Class Imbalance.

Zeynep Sonat Baltaci, Kemal Oksuz, Selim Kuzucu, K. Tezoren, B. K. Konar, A. Ozkan, Emre Akbas, Sinan Kalkan

CoRR, 2023

Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation.

Francisco Eiras, Kemal Oksuz, Adel Bibi, Philip H. S. Torr, Puneet K. Dokania

CoRR, 2023

MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection.

Kemal Oksuz, Selim Kuzucu, Tom Joy, Puneet K. Dokania

CoRR, 2023

Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration.

Kemal Oksuz, Tom Joy, Puneet K. Dokania

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Correlation Loss: Enforcing Correlation between Classification and Localization.

Fehmi Kahraman, Kemal Oksuz, Sinan Kalkan, Emre Akbas

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

One Metric to Measure Them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks.

Kemal Oksuz, Baris Can Cam, Sinan Kalkan, Emre Akbas

IEEE Trans. Pattern Anal. Mach. Intell., 2022

2021

Identifying and addressing imbalance problems in visual detection (Görsel tespitteki dengesizlik problemlerinin belirlenmesi ve çözümlenmesi)

Kemal Oksuz

PhD thesis, 2021

Imbalance Problems in Object Detection: A Review.

Kemal Oksuz, Baris Can Cam, Sinan Kalkan, Emre Akbas

IEEE Trans. Pattern Anal. Mach. Intell., 2021

Rank & Sort Loss for Object Detection and Instance Segmentation.

Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation.

Kemal Oksuz, Baris Can Cam, Fehmi Kahraman, Zeynep Sonat Baltaci, Sinan Kalkan, Emre Akbas

Proceedings of the 32nd British Machine Vision Conference 2021, 2021

2020

Generating Positive Bounding Boxes for Balanced Training of Object Detectors.

Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2020

A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection.

Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2018

Localization Recall Precision (LRP): A New Performance Metric for Object Detection.

Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan

Proceedings of the Computer Vision - ECCV 2018, 2018

2017

Deficiency aware subpattern assignment.

Kemal Oksuz, Ali Taylan Cemgil

Proceedings of the 25th Signal Processing and Communications Applications Conference, 2017

2016

The comparison of the performances of global nearest neighbor and probability hypothesis density filter for varying clutter rates.

Kemal Oksuz, Ali Taylan Cemgil

Proceedings of the 24th Signal Processing and Communication Application Conference, 2016