27 citations · 47 across the 16 of their papers we have counts for
17 papers
Less Language, More Latents: Annotation-Efficient VLAs for Driving
Alexey Zakharov, Kemal Oksuz, Puneet K. Dokania
Vision-language-action models (VLA) promise human-steerable autonomous driving, but their training is bottlenecked by the scarcity of frames paired with natural-language instructio…
Foundation Models for Trajectory Planning in Autonomous Driving: A Review of Progress and Open Challenges
Kemal Oksuz, Alexandru Buburuzan, Anthony Knittel +2
The emergence of multi-modal foundation models has markedly transformed the technology for autonomous driving, shifting away from conventional and mostly hand-crafted design choice…
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz +4
Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via…
Bucketed Ranking-based Losses for Efficient Training of Object Detectors
Feyza Yavuz, Baris Can Cam, Adnan Harun Dogan +3
Ranking-based loss functions, such as Average Precision Loss and Rank&Sort Loss, outperform widely used score-based losses in object detection. These loss functions better align wi…
On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines
Selim Kuzucu, Kemal Oksuz, Jonathan Sadeghi +1
Reliable usage of object detectors require them to be calibrated -- a crucial problem that requires careful attention. Recent approaches towards this involve (1) designing new loss…
Class Uncertainty: A Measure to Mitigate Class Imbalance
Z. S. Baltaci, K. Oksuz, S. Kuzucu +5
Class-wise characteristics of training examples affect the performance of deep classifiers. A well-studied example is when the number of training examples of classes follows a long…
Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation
Francisco Eiras, Kemal Oksuz, Adel Bibi +2
Referring Image Segmentation (RIS) - the problem of identifying objects in images through natural language sentences - is a challenging task currently mostly solved through supervi…
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
Kemal Oksuz, Selim Kuzucu, Tom Joy +1
Combining the strengths of many existing predictors to obtain a Mixture of Experts which is superior to its individual components is an effective way to improve the performance wit…
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
Kemal Oksuz, Tom Joy, Puneet K. Dokania
The current approach for testing the robustness of object detectors suffers from serious deficiencies such as improper methods of performing out-of-distribution detection and using…
Correlation Loss: Enforcing Correlation between Classification and Localization
Fehmi Kahraman, Kemal Oksuz, Sinan Kalkan +1
Object detectors are conventionally trained by a weighted sum of classification and localization losses. Recent studies (e.g., predicting IoU with an auxiliary head, Generalized Fo…
Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation
Kemal Oksuz, Baris Can Cam, Fehmi Kahraman +3
This paper presents Mask-aware Intersection-over-Union (maIoU) for assigning anchor boxes as positives and negatives during training of instance segmentation methods. Unlike conven…
Rank & Sort Loss for Object Detection and Instance Segmentation
Kemal Oksuz, Baris Can Cam, Emre Akbas +1
We propose Rank & Sort (RS) Loss, a ranking-based loss function to train deep object detection and instance segmentation methods (i.e. visual detectors). RS Loss supervises the cla…
One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks
Kemal Oksuz, Baris Can Cam, Sinan Kalkan +1
Despite being widely used as a performance measure for visual detection tasks, Average Precision (AP) is limited in (i) reflecting localisation quality, (ii) interpretability and (…
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection
Kemal Oksuz, Baris Can Cam, Emre Akbas +1
We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detec…
Generating Positive Bounding Boxes for Balanced Training of Object Detectors
Kemal Oksuz, Baris Can Cam, Emre Akbas +1
Two-stage deep object detectors generate a set of regions-of-interest (RoI) in the first stage, then, in the second stage, identify objects among the proposed RoIs that sufficientl…
Imbalance Problems in Object Detection: A Review
Kemal Oksuz, Baris Can Cam, Sinan Kalkan +1
In this paper, we present a comprehensive review of the imbalance problems in object detection. To analyze the problems in a systematic manner, we introduce a problem-based taxonom…
Localization Recall Precision (LRP): A New Performance Metric for Object Detection
Kemal Oksuz, Baris Can Cam, Emre Akbas +1
Average precision (AP), the area under the recall-precision (RP) curve, is the standard performance measure for object detection. Despite its wide acceptance, it has a number of sh…