27 citations · 85 across the 19 of their papers we have counts for
24 papers
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…
AssembleRL: Learning to Assemble Furniture from Their Point Clouds
Özgür Aslan, Burak Bolat, Batuhan Bal +3
The rise of simulation environments has enabled learning-based approaches for assembly planning, which is otherwise a labor-intensive and daunting task. Assembling furniture is esp…
Segment Augmentation and Differentiable Ranking for Logo Retrieval
Feyza Yavuz, Sinan Kalkan
Logo retrieval is a challenging problem since the definition of similarity is more subjective compared to image retrieval tasks and the set of known similarities is very scarce. To…
Does depth estimation help object detection?
Bedrettin Cetinkaya, Sinan Kalkan, Emre Akbas
Ground-truth depth, when combined with color data, helps improve object detection accuracy over baseline models that only use color. However, estimated depth does not always yield…
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…
Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection
Faisal Alamri, Sinan Kalkan, Nicolas Pugeault
Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures…
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 (…
Spatio-Temporal Analysis of Facial Actions using Lifecycle-Aware Capsule Networks
Nikhil Churamani, Sinan Kalkan, Hatice Gunes
Most state-of-the-art approaches for Facial Action Unit (AU) detection rely upon evaluating facial expressions from static frames, encoding a snapshot of heightened facial activity…
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…
Investigating Bias and Fairness in Facial Expression Recognition
Tian Xu, Jennifer White, Sinan Kalkan +1
Recognition of expressions of emotions and affect from facial images is a well-studied research problem in the fields of affective computing and computer vision with a large number…
Mind Your Manners! A Dataset and A Continual Learning Approach for Assessing Social Appropriateness of Robot Actions
Jonas Tjomsland, Sinan Kalkan, Hatice Gunes
To date, endowing robots with an ability to assess social appropriateness of their actions has not been possible. This has been mainly due to (i) the lack of relevant and labelled…
ALET (Automated Labeling of Equipment and Tools): A Dataset, a Baseline and a Usecase for Tool Detection in the Wild
Fatih Can Kurnaz, Burak Hocaoğlu, Mert Kaan Yılmaz +2
Robots collaborating with humans in realistic environments will need to be able to detect the tools that can be used and manipulated. However, there is no available dataset or stud…
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…
Searching for Ambiguous Objects in Videos using Relational Referring Expressions
Hazan Anayurt, Sezai Artun Ozyegin, Ulfet Cetin +2
Humans frequently use referring (identifying) expressions to refer to objects. Especially in ambiguous settings, humans prefer expressions (called relational referring expressions)…
Learning to Generate Unambiguous Spatial Referring Expressions for Real-World Environments
Fethiye Irmak Doğan, Sinan Kalkan, Iolanda Leite
Referring to objects in a natural and unambiguous manner is crucial for effective human-robot interaction. Previous research on learning-based referring expressions has focused pri…
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…
COSMO: Contextualized Scene Modeling with Boltzmann Machines
Ilker Bozcan, Sinan Kalkan
Scene modeling is very crucial for robots that need to perceive, reason about and manipulate the objects in their environments. In this paper, we adapt and extend Boltzmann Machine…
What is (missing or wrong) in the scene? A Hybrid Deep Boltzmann Machine For Contextualized Scene Modeling
İlker Bozcan, Yağmur Oymak, İdil Zeynep Alemdar +1
Scene models allow robots to reason about what is in the scene, what else should be in it, and what should not be in it. In this paper, we propose a hybrid Boltzmann Machine (BM) f…
CINet: A Learning Based Approach to Incremental Context Modeling in Robots
Fethiye Irmak Doğan, İlker Bozcan, Mehmet Çelik +1
There have been several attempts at modeling context in robots. However, either these attempts assume a fixed number of contexts or use a rule-based approach to determine when to i…
A Deep Incremental Boltzmann Machine for Modeling Context in Robots
Fethiye Irmak Doğan, Hande Çelikkanat, Sinan Kalkan
Context is an essential capability for robots that are to be as adaptive as possible in challenging environments. Although there are many context modeling efforts, they assume a fi…
Using Deep Networks for Drone Detection
Cemal Aker, Sinan Kalkan
Drone detection is the problem of finding the smallest rectangle that encloses the drone(s) in a video sequence. In this study, we propose a solution using an end-to-end object det…
A Large-scale Dataset and Benchmark for Similar Trademark Retrieval
Osman Tursun, Cemal Aker, Sinan Kalkan
Trademark retrieval (TR) has become an important yet challenging problem due to an ever increasing trend in trademark applications and infringement incidents. There have been many…