Kemal Oksuz
9 papers · 2018–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (19) π Cross-Pollinator (4) π Renaissance Researcher (5) π Interdisciplinary Bridge π§ Keyword Pioneer
π
Conference Polyglot
(6)
π
Academic Marathon
(6)
π
Conference Pioneer
β
The Questioner
Conferences
ECCV (3)
NIPS (2)
AAAI (1)
CVPR (1)
ICCV (1)
WACV (1)
Top co-authors
Keywords
object detection
(5)
loss function
(3)
direct preference optimization
(1)
preference alignment
(1)
preference optimization
(1)
autonomous driving
(1)
instance segmentation
(1)
neural network optimization
(1)
learning to rank
(1)
correlation coefficient
(1)
classification loss
(1)
region of interest
(1)
region proposal
(1)
out-of-distribution detection
(1)
mechanistic interpretability
(1)
safety fine-tuning
(1)
domain shift
(1)
bounding box
(1)
adversarial input
(1)
mlp weight transformation
(1)
Papers
Bucketed Ranking-based Losses for Efficient Training of Object Detectors
ECCV 2024
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
NIPS 2024
"On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines"
ECCV 2024
Correlation Loss: Enforcing Correlation between Classification and Localization
AAAI 2023
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
CVPR 2023
Rank & Sort Loss for Object Detection and Instance Segmentation
ICCV 2021
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection
NIPS 2020
Generating Positive Bounding Boxes for Balanced Training of Object Detectors
WACV 2020
Localization Recall Precision (LRP): A New Performance Metric for Object Detection
ECCV 2018