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 • 9 Apr 2023 • Amir Nazemi, Zeyad Moustafa, Paul Fieguth
Continual learning in real-world scenarios is a major challenge.
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 • 8 Jun 2018 • Amir Nazemi, Mohammad Javad Shafiee, Zohreh Azimifar, Alexander Wong
Here, we formulate the vehicle make and model recognition as a fine-grained classification problem and propose a new configurable on-road vehicle make and model recognition framework.