1 code implementation • 11 Oct 2023 • Caleb Tung, Nicholas Eliopoulos, Purvish Jajal, Gowri Ramshankar, Chen-Yun Yang, Nicholas Synovic, Xuecen Zhang, Vipin Chaudhary, George K. Thiruvathukal, Yung-Hsiang Lu
Computer vision often uses highly accurate Convolutional Neural Networks (CNNs), but these deep learning models are associated with ever-increasing energy and computation requirements.
1 code implementation • 17 Aug 2022 • Kartikeya Bhardwaj, James Ward, Caleb Tung, Dibakar Gope, Lingchuan Meng, Igor Fedorov, Alex Chalfin, Paul Whatmough, Danny Loh
To address this question, we propose a new paradigm called Restructurable Activation Networks (RANs) that manipulate the amount of non-linearity in models to improve their hardware-awareness and efficiency.
no code implementations • 28 Jul 2022 • Caleb Tung, Abhinav Goel, Fischer Bordwell, Nick Eliopoulos, Xiao Hu, George K. Thiruvathukal, Yung-Hsiang Lu
Using this method, we show that the consistency of modern object detectors ranges from 83. 2% to 97. 1% on different video datasets from the Multiple Object Tracking Challenge.
no code implementations • 21 Jul 2022 • Caleb Tung, Abhinav Goel, Xiao Hu, Nicholas Eliopoulos, Emmanuel Amobi, George K. Thiruvathukal, Vipin Chaudhary, Yung-Hsiang Lu
We observe that, given a computer vision task, images often contain pixels that are irrelevant to the task.
1 code implementation • 27 Sep 2021 • Abhinav Goel, Caleb Tung, Xiao Hu, George K. Thiruvathukal, James C. Davis, Yung-Hsiang Lu
We design a novel method that creates a parallel inference pipeline for computer vision problems that use hierarchical DNNs.
1 code implementation • 19 Jun 2021 • Abhinav Goel, Caleb Tung, Xiao Hu, Haobo Wang, James C. Davis, George K. Thiruvathukal, Yung-Hsiang Lu
At each node in the hierarchy, a small DNN identifies a different attribute of the query image.
no code implementations • 27 Aug 2020 • Isha Ghodgaonkar, Subhankar Chakraborty, Vishnu Banna, Shane Allcroft, Mohammed Metwaly, Fischer Bordwell, Kohsuke Kimura, Xinxin Zhao, Abhinav Goel, Caleb Tung, Akhil Chinnakotla, Minghao Xue, Yung-Hsiang Lu, Mark Daniel Ward, Wei Zakharov, David S. Ebert, David M. Barbarash, George K. Thiruvathukal
This research team has created methods that can discover thousands of network cameras worldwide, retrieve data from the cameras, analyze the data, and report the sizes of crowds as different countries issued and lifted restrictions (also called ''lockdown'').
no code implementations • 2 Jul 2020 • Abhinav Goel, Caleb Tung, Sara Aghajanzadeh, Isha Ghodgaonkar, Shreya Ghosh, George K. Thiruvathukal, Yung-Hsiang Lu
Object counting takes two inputs: an image and an object query and reports the number of occurrences of the queried object.
no code implementations • 24 Mar 2020 • Abhinav Goel, Caleb Tung, Yung-Hsiang Lu, George K. Thiruvathukal
Deep neural networks (DNNs) are successful in many computer vision tasks.
no code implementations • 31 Dec 2018 • Caleb Tung, Matthew R. Kelleher, Ryan J. Schlueter, Binhan Xu, Yung-Hsiang Lu, George K. Thiruvathukal, Yen-Kuang Chen, Yang Lu
However, the images found in those datasets, are independent of one another and cannot be used to test YOLO's consistency at detecting the same object as its environment (e. g. ambient lighting) changes.