1 code implementation • IEEE Access 2023 • Ala Shaabana, Zahra Gharaee, Paul Fieguth
Secondly, classifiers trained by a single, monolithic neural network often lack stability and generalization.
no code implementations • 20 Dec 2023 • Xin Xu, JinMan Park, Paul Fieguth
Single-image super-resolution (SISR) has seen significant advancements through the integration of deep learning.
no code implementations • 15 Nov 2023 • Dylan Spicker, Amir Nazemi, Joy Hutchinson, Paul Fieguth, Sharon I. Kirkpatrick, Michael Wallace, Kevin W. Dodd
In this work, we demonstrate the ways in which measurement error erodes the performance of neural networks, and illustrate the care that is required for leveraging these models in the presence of error.
no code implementations • 26 Sep 2023 • Amir Nazemi, Mohammad Javad Shafiee, Zahra Gharaee, Paul Fieguth
We propose two novel techniques to reduce the memory requirement of Online VOS methods while improving modeling accuracy and generalization on long videos.
1 code implementation • NeurIPS 2023 • Zahra Gharaee, ZeMing Gong, Nicholas Pellegrino, Iuliia Zarubiieva, Joakim Bruslund Haurum, Scott C. Lowe, Jaclyn T. A. McKeown, Chris C. Y. Ho, Joschka McLeod, Yi-Yun C Wei, Jireh Agda, Sujeevan Ratnasingham, Dirk Steinke, Angel X. Chang, Graham W. Taylor, Paul Fieguth
In an effort to catalog insect biodiversity, we propose a new large dataset of hand-labelled insect images, the BIOSCAN-Insect Dataset.
no code implementations • 4 Jul 2023 • Marian Boktor, James E. D. Tweel, Benjamin R. Ecclestone, Jennifer Ai Ye, Paul Fieguth, Parsin Haji Reza
Experimental results reveal that specific combinations of features outperform the conventional channels by improving the labeling of tissue structures prior to model training.
no code implementations • 2 Jun 2023 • JinMan Park, Francois Barnard, Saad Hossain, Sirisha Rambhatla, Paul Fieguth
Unsupervised domain adaptation (UDA) aims to bridge the gap between source and target domains in the absence of target domain labels using two main techniques: input-level alignment (such as generative modeling and stylization) and feature-level alignment (which matches the distribution of the feature maps, e. g. gradient reversal layers).
1 code implementation • 9 Apr 2023 • Amir Nazemi, Zeyad Moustafa, Paul Fieguth
Continual learning in real-world scenarios is a major challenge.
no code implementations • 4 Nov 2022 • Nicholas Pellegrino, Zahra Gharaee, Paul Fieguth
The BIOSCAN project, led by the International Barcode of Life Consortium, seeks to study changes in biodiversity on a global scale.
no code implementations • 9 Jun 2022 • JinMan Park, Kimathi Kaai, Saad Hossain, Norikatsu Sumi, Sirisha Rambhatla, Paul Fieguth
Egocentric 3D human pose estimation (HPE) from images is challenging due to severe self-occlusions and strong distortion introduced by the fish-eye view from the head mounted camera.
no code implementations • 4 Mar 2022 • Marian Boktor, Benjamin Ecclestone, Vlad Pekar, Deepak Dinakaran, John R. Mackey, Paul Fieguth, Parsin Haji Reza
We use a Pix2Pix generative adversarial network (GAN) to develop visualizations analogous to H&E staining from label-free TA-PARS images.
no code implementations • 15 Feb 2022 • Nicholas Pellegrino, Paul Fieguth, Parsin Haji Reza
Many measurement modalities which perform imaging by probing an object pixel-by-pixel, such as via Photoacoustic Microscopy, produce a multi-dimensional feature (typically a time-domain signal) at each pixel.
no code implementations • 7 Nov 2021 • Shima Kamyab, Zohreh Azimifar, Rasool Sabzi, Paul Fieguth
In this paper we investigate a variety of deep learning strategies for solving inverse problems.
no code implementations • 27 Jan 2021 • Wei Chen, Yu Liu, Weiping Wang, Erwin Bakker, Theodoros Georgiou, Paul Fieguth, Li Liu, Michael S. Lew
In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.
no code implementations • 12 Nov 2020 • Moloud Abdar, Farhad Pourpanah, Sadiq Hussain, Dana Rezazadegan, Li Liu, Mohammad Ghavamzadeh, Paul Fieguth, Xiaochun Cao, Abbas Khosravi, U Rajendra Acharya, Vladimir Makarenkov, Saeid Nahavandi
Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes.
no code implementations • 21 Sep 2020 • Benjamin R. Ecclestone, Kevan Bell, Saad Abbasi, Deepak Dinakaran, Frank K. H. van Landeghem, John R. Mackey, Paul Fieguth, Parsin Haji Reza
Images obtained using this technique show comparable quality and contrast to the current standard for histopathological assessment of brain tissues.
1 code implementation • 8 Jun 2020 • Zobeir Raisi, Mohamed A. Naiel, Paul Fieguth, Steven Wardell, John Zelek
Thus, unlike previous surveys in this field, the objectives of this survey are as follows: first, offering the reader not only a review on the recent advancement in scene text detection and recognition, but also presenting the results of conducting extensive experiments using a unified evaluation framework that assesses pre-trained models of the selected methods on challenging cases, and applies the same evaluation criteria on these techniques.
no code implementations • 4 Mar 2020 • Mohammad Javad Shafiee, Ahmadreza Jeddi, Amir Nazemi, Paul Fieguth, Alexander Wong
This paper analyzes the robustness of deep learning models in autonomous driving applications and discusses the practical solutions to address that.
no code implementations • 13 Dec 2019 • Amir Nazemi, Paul Fieguth
Deep convolutional neural networks can be highly vulnerable to small perturbations of their inputs, potentially a major issue or limitation on system robustness when using deep networks as classifiers.
no code implementations • 19 Apr 2019 • Audrey Chung, Paul Fieguth, Alexander Wong
Evolutionary deep intelligence has recently shown great promise for producing small, powerful deep neural network models via the synthesis of increasingly efficient architectures over successive generations.
no code implementations • 19 Nov 2018 • Audrey Chung, Paul Fieguth, Alexander Wong
Evolutionary deep intelligence has recently shown great promise for producing small, powerful deep neural network models via the organic synthesis of increasingly efficient architectures over successive generations.
no code implementations • 14 Nov 2018 • Xiaodan Hu, Audrey G. Chung, Paul Fieguth, Farzad Khalvati, Masoom A. Haider, Alexander Wong
Generative Adversarial Networks (GANs) have shown considerable promise for mitigating the challenge of data scarcity when building machine learning-driven analysis algorithms.
no code implementations • 6 Sep 2018 • Li Liu, Wanli Ouyang, Xiaogang Wang, Paul Fieguth, Jie Chen, Xinwang Liu, Matti Pietikäinen
Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images.
no code implementations • 13 Feb 2018 • Li Liu, Jie Chen, Guoying Zhao, Paul Fieguth, Xilin Chen, Matti Pietikäinen
Because extreme scale variations are not necessarily present in most standard texture databases, to support the proposed extreme-scale aspects of texture understanding we are developing a new dataset, the Extreme Scale Variation Textures (ESVaT), to test the performance of our framework.
no code implementations • 9 Feb 2018 • Audrey G. Chung, Paul Fieguth, Alexander Wong
Evolutionary deep intelligence synthesizes highly efficient deep neural networks architectures over successive generations.
no code implementations • 31 Jan 2018 • Li Liu, Jie Chen, Paul Fieguth, Guoying Zhao, Rama Chellappa, Matti Pietikainen
Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention.
no code implementations • 7 Sep 2017 • Audrey Chung, Mohammad Javad Shafiee, Paul Fieguth, Alexander Wong
Evolutionary deep intelligence was recently proposed as a method for achieving highly efficient deep neural network architectures over successive generations.
no code implementations • 18 Dec 2015 • Mohammad Javad Shafiee, Parthipan Siva, Paul Fieguth, Alexander Wong
Transfer learning is a recent field of machine learning research that aims to resolve the challenge of dealing with insufficient training data in the domain of interest.
no code implementations • 11 Dec 2015 • Mohammad Javad Shafiee, Parthipan Siva, Paul Fieguth, Alexander Wong
Experimental results show that features learned using deep convolutional StochasticNets, with fewer neural connections than conventional deep convolutional neural networks, can allow for better or comparable classification accuracy than conventional deep neural networks: relative test error decrease of ~4. 5% for classification on the STL-10 dataset and ~1% for classification on the SVHN dataset.
no code implementations • 30 Jun 2015 • Mohammad Javad Shafiee, Alexander Wong, Paul Fieguth
However, the issue of computational tractability becomes a significant issue when incorporating such long-range nodal interactions, particularly when a large number of long-range nodal interactions (e. g., fully-connected random fields) are modeled.