Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Temel, Dogancan"'
Semantic segmentation is a scene understanding task at the heart of safety-critical applications where robustness to corrupted inputs is essential. Implicit Background Estimation (IBE) has demonstrated to be a promising technique to improve the robus
Externí odkaz:
http://arxiv.org/abs/2009.00817
In this paper, we propose a model-based characterization of neural networks to detect novel input types and conditions. Novelty detection is crucial to identify abnormal inputs that can significantly degrade the performance of machine learning algori
Externí odkaz:
http://arxiv.org/abs/2008.06094
Visual explanations are logical arguments based on visual features that justify the predictions made by neural networks. Current modes of visual explanations answer questions of the form $`Why \text{ } P?'$. These $Why$ questions operate under broad
Externí odkaz:
http://arxiv.org/abs/2008.00178
Learning representations that clearly distinguish between normal and abnormal data is key to the success of anomaly detection. Most of existing anomaly detection algorithms use activation representations from forward propagation while not exploiting
Externí odkaz:
http://arxiv.org/abs/2007.09507
Traffic signs are critical for maintaining the safety and efficiency of our roads. Therefore, we need to carefully assess the capabilities and limitations of automated traffic sign detection systems. Existing traffic sign datasets are limited in term
Externí odkaz:
http://arxiv.org/abs/1908.11262
In this paper, we utilize weight gradients from backpropagation to characterize the representation space learned by deep learning algorithms. We demonstrate the utility of such gradients in applications including perceptual image quality assessment a
Externí odkaz:
http://arxiv.org/abs/1908.09998
Abnormalities in pupillary light reflex can indicate optic nerve disorders that may lead to permanent visual loss if not diagnosed in an early stage. In this study, we focus on relative afferent pupillary defect (RAPD), which is based on the differen
Externí odkaz:
http://arxiv.org/abs/1908.02300
Scene understanding and semantic segmentation are at the core of many computer vision tasks, many of which, involve interacting with humans in potentially dangerous ways. It is therefore paramount that techniques for principled design of robust model
Externí odkaz:
http://arxiv.org/abs/1905.13306
Publikováno v:
International Symposium on Medical Robotics (ISMR), Atlanta, GA, USA, 2019, pp. 1-7
In this paper, we introduce a portable eye imaging device denoted as lab-on-a-headset, which can automatically perform a swinging flashlight test. We utilized this device in a clinical study to obtain high-resolution recordings of eyes while they are
Externí odkaz:
http://arxiv.org/abs/1905.08886
State-of-the-art algorithms successfully localize and recognize traffic signs over existing datasets, which are limited in terms of challenging condition type and severity. Therefore, it is not possible to estimate the performance of traffic sign det
Externí odkaz:
http://arxiv.org/abs/1902.06857