1 code implementation • 2 Sep 2020 • Charles Lehman, Dogancan Temel, Ghassan AlRegib
Semantic segmentation is a scene understanding task at the heart of safety-critical applications where robustness to corrupted inputs is essential.
no code implementations • 13 Aug 2020 • Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
To articulate the significance of the model perspective in novelty detection, we utilize backpropagated gradients.
3 code implementations • 1 Aug 2020 • Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib
Current modes of visual explanations answer questions of the form $`Why \text{ } P?'$.
2 code implementations • ECCV 2020 • Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
Anomalies require more drastic model updates to fully represent them compared to normal data.
no code implementations • ICLR 2020 • Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
To complement the learned information from activation-based representation, we propose utilizing a gradient-based representation that explicitly focuses on missing information.
no code implementations • 25 Sep 2019 • Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib
Such a positioning scheme is based on a data point’s second-order property.
2 code implementations • 29 Aug 2019 • Dogancan Temel, Min-Hung Chen, Ghassan AlRegib
We investigate the effect of challenging conditions through spectral analysis and show that challenging conditions can lead to distinct magnitude spectrum characteristics.
2 code implementations • 27 Aug 2019 • Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
In this paper, we utilize weight gradients from backpropagation to characterize the representation space learned by deep learning algorithms.
no code implementations • 6 Aug 2019 • Dogancan Temel, Melvin J. Mathew, Ghassan AlRegib, Yousuf M. Khalifa
Based on the conducted experiments, proposed algorithm RAPDNet can achieve a sensitivity and a specificity of 90. 6% over 64 test cases in a balanced set, which corresponds to an AUC of 0. 929 in ROC analysis.
1 code implementation • 23 May 2019 • Charles Lehman, Dogancan Temel, Ghassan AlRegib
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.
no code implementations • 21 May 2019 • Dogancan Temel, Melvin J. Mathew, Ghassan AlRegib, Yousuf M. Khalifa
In this paper, we introduce a portable eye imaging device denoted as lab-on-a-headset, which can automatically perform a swinging flashlight test.
2 code implementations • 19 Feb 2019 • Dogancan Temel, Tariq Alshawi, Min-Hung Chen, Ghassan AlRegib
Experimental results show that benchmarked algorithms are highly sensitive to tested challenging conditions, which result in an average performance drop of 0. 17 in terms of precision and a performance drop of 0. 28 in recall under severe conditions.
1 code implementation • 18 Feb 2019 • Dogancan Temel, Jinsol Lee, Ghassan AlRegib
Experimental results show that deep learning-based image representations can estimate the recognition performance variation with a Spearman's rank-order correlation of 0. 94 under multifarious acquisition conditions.
no code implementations • 17 Feb 2019 • Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib
In this paper, we generate and control semantically interpretable filters that are directly learned from natural images in an unsupervised fashion.
1 code implementation • 22 Nov 2018 • Dogancan Temel, Ghassan AlRegib
In this work, we combine these approaches by extending CIEDE2000 formula with perceptual color difference to assess image quality.
2 code implementations • 21 Nov 2018 • Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
We use multiple linear decoders to capture different abstraction levels of the image patches.
1 code implementation • 21 Nov 2018 • Dogancan Temel, Ghassan AlRegib
In addition to support vector machines that are commonly used in the multi-method fusion, we propose using neural networks in the boosting.
1 code implementation • 21 Nov 2018 • Dogancan Temel, Ghassan AlRegib
In this work, we compare the state of the art quality and content-based spatial pooling strategies and show that although features are the key in any image quality assessment, pooling also matters.
no code implementations • 21 Nov 2018 • Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
While assessing image quality, the filters need to capture perceptual differences based on dissimilarities between a reference image and its distorted version.
no code implementations • 19 Nov 2018 • Dogancan Temel, Ghassan AlRegib
We show that generic descriptors can perform as well as state of the art hand-crafted aesthetics models that use global features.
no code implementations • 18 Nov 2018 • Dogancan Temel, Ghassan AlRegib
An average observer perceives the world in color instead of black and white.
1 code implementation • 16 Nov 2018 • Dogancan Temel, Ghassan AlRegib
Moreover, BleSS significantly enhances the performance of SR-SIM and FSIM in the full TID 2013 database.
1 code implementation • 14 Nov 2018 • Dogancan Temel, Ghassan AlRegib
In terms of the Pearson and the Spearman correlation, ReSIFT is the best performing quality estimator in the overall databases.
1 code implementation • 19 Oct 2018 • Huijie Pan, Dogancan Temel, Ghassan AlRegib
In this paper, we propose an algorithm denoted as HeartBEAT that tracks heart rate from wrist-type photoplethysmography (PPG) signals and simultaneously recorded three-axis acceleration data.
1 code implementation • 18 Oct 2018 • Dogancan Temel, Jinsol Lee, Ghassan AlRegib
Moreover, we investigate the relationship between object recognition and image quality and show that objective quality algorithms can estimate recognition performance under certain photometric challenging conditions.
no code implementations • 15 Oct 2018 • Dogancan Temel, Ghassan AlRegib
This paper presents a full-reference image quality estimator based on color, structure, and visual system characteristics denoted as CSV.
1 code implementation • 15 Oct 2018 • Dogancan Temel, Ghassan AlRegib
Robust and reliable traffic sign detection is necessary to bring autonomous vehicles onto our roads.
no code implementations • 14 Oct 2018 • Dogancan Temel, Ghassan AlRegib
To overcome these shortcomings, we introduce an image quality assessment algorithm based on the Spectral Understanding of Multi-scale and Multi-channel Error Representations, denoted as SUMMER.
1 code implementation • 7 Dec 2017 • Dogancan Temel, Gukyeong Kwon, Mohit Prabhushankar, Ghassan AlRegib
We benchmark the performance of existing solutions in real-world scenarios and analyze the performance variation with respect to challenging conditions.