Kemal Öksüz

Computer Science · Physical Sciences

6h-index168citations33works1.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(23), Domain Adaptation and Few-Shot Learning(14), Advanced Image and Video Retrieval Techniques(11), Adversarial Robustness in Machine Learning(9), Target Tracking and Data Fusion in Sensor Networks(3)

Publications33 total

Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation
Lecture notes in computer science·2025
Bucketed Ranking-Based Losses for Efficient Training of Object Detectors
Lecture notes in computer science·2024· 1 citedOpen Access
On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines
Lecture notes in computer science·2024· 2 cited
Bucketed Ranking-based Losses for Efficient Training of Object Detectors
arXiv (Cornell University)·2024· 1 citedOpen Access
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
arXiv (Cornell University)·2024· 3 citedOpen Access
On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines
arXiv (Cornell University)·2024Open Access
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
2024
Generalized Mask-aware IoU for Anchor Assignment for Real-time Instance Segmentation
arXiv (Cornell University)·2023Open Access
Class Uncertainty: A Measure to Mitigate Class Imbalance
arXiv (Cornell University)·2023Open Access
Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation
arXiv (Cornell University)·2023Open Access
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
arXiv (Cornell University)·2023· 3 citedOpen Access
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
arXiv (Cornell University)·2023Open Access
Correlation Loss: Enforcing Correlation between Classification and Localization
Proceedings of the AAAI Conference on Artificial Intelligence·2023· 6 citedOpen Access
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
2023· 12 cited
Correlation Loss: Enforcing Correlation between Classification and Localization
arXiv (Cornell University)·2023Open Access
One Metric to Measure Them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks
IEEE Transactions on Pattern Analysis and Machine Intelligence·2021· 8 citedOpen Access
Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation
arXiv (Cornell University)·2021· 3 citedOpen Access
Rank & Sort Loss for Object Detection and Instance Segmentation
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 41 citedOpen Access
Rank & Sort Loss for Object Detection and Instance Segmentation
arXiv (Cornell University)·2021· 6 citedOpen Access
Rank & Sort Loss for Object Detection and Instance Segmentation
arXiv (Cornell University)·2021Open Access
page 1 of 2Next →

Frequent Co-authors

Emre Akbaş(20), Sinan Kalkan(20), Barış Can Çam(17), Puneet K. Dokania(9), Fehmi Kahraman(5), Zeynep Sonat Baltacı(4), Selim Kuzucu(4), Tom Joy(3), Ali Taylan Cemgil(3), Philip H. S. Torr(3), Samyak Jain(2), Ekdeep Singh Lubana(2), Tom Joy(2), Amartya Sanyal(2), Jonathan Sadeghi(2), Feyza Yavuz(2), Adnan Harun Dogan(2), Francisco Eiras(2), Adel Bibi(2), Philip H. S. Torr(1)