Zobrazeno 1 - 10
of 13 296
pro vyhledávání: '"Kalkan, A."'
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 with the evaluation criteria, have fewer hyperparameters, and offer robu
Externí odkaz:
http://arxiv.org/abs/2407.14204
Autor:
Akin, Ali, Kalkan, Habil
Traffic accidents, causing millions of deaths and billions of dollars in economic losses each year globally, have become a significant issue. One of the main causes of these accidents is drivers being sleepy or fatigued. Recently, various studies hav
Externí odkaz:
http://arxiv.org/abs/2407.02222
In many applications, a mobile manipulator robot is required to grasp a set of objects distributed in space. This may not be feasible from a single base pose and the robot must plan the sequence of base poses for grasping all objects, minimizing the
Externí odkaz:
http://arxiv.org/abs/2406.08653
Autor:
Shakir, Hafiz Muhammad, Suleiman, Abdulsalam Aji, Kalkan, Kübra Nur, Parsi, Amir, Başçı, Uğur, Durmuş, Mehmet Atıf, Ölçer, Ahmet Osman, Korkut, Hilal, Sevik, Cem, Sarpkaya, İbrahim, Kasırga, Talip Serkan
Excitons in monolayer transition metal dichalcogenides (TMDCs) offer intriguing new possibilities for optoelectronics with no analogues in bulk semiconductors. Yet, intrinsic defects in TMDCs limit the radiative exciton recombination pathways. As a r
Externí odkaz:
http://arxiv.org/abs/2405.20636
Heatmaps have been instrumental in helping understand deep network decisions, and are a common approach for Explainable AI (XAI). While significant progress has been made in enhancing the informativeness and accessibility of heatmaps, heatmap analysi
Externí odkaz:
http://arxiv.org/abs/2405.13264
We introduce, XoFTR, a cross-modal cross-view method for local feature matching between thermal infrared (TIR) and visible images. Unlike visible images, TIR images are less susceptible to adverse lighting and weather conditions but present difficult
Externí odkaz:
http://arxiv.org/abs/2404.09692
Detecting edges in images suffers from the problems of (P1) heavy imbalance between positive and negative classes as well as (P2) label uncertainty owing to disagreement between different annotators. Existing solutions address P1 using class-balanced
Externí odkaz:
http://arxiv.org/abs/2403.01795
Autor:
Çam, Barış Can, Öksüz, Kemal, Kahraman, Fehmi, Baltacı, Zeynep Sonat, Kalkan, Sinan, Akbaş, Emre
This paper introduces Generalized Mask-aware Intersection-over-Union (GmaIoU) as a new measure for positive-negative assignment of anchor boxes during training of instance segmentation methods. Unlike conventional IoU measure or its variants, which o
Externí odkaz:
http://arxiv.org/abs/2312.17031
Unfair predictions of machine learning (ML) models impede their broad acceptance in real-world settings. Tackling this arduous challenge first necessitates defining what it means for an ML model to be fair. This has been addressed by the ML community
Externí odkaz:
http://arxiv.org/abs/2312.11299
Autor:
Kalkan, Nurcan Kutluk, Ozdemir, Ilkay, Yuksel, Yusuf, Akinci, Umit, Barth, Johannes V., Aktürk, Ethem
We present a comprehensive study on the electronic and magnetic properties of the EuCl$_3$ monolayer using first-principles calculations. By taking into account the spin-orbit coupling (SOC) and the Hubbard effects, we elucidate the influence of thes
Externí odkaz:
http://arxiv.org/abs/2312.05018