9 papers
Challenges and Obstacles Towards Deploying Deep Learning Models on Mobile Devices
Hamid Tabani, Ajay Balasubramaniam, Elahe Arani +1
From computer vision and speech recognition to forecasting trajectories in autonomous vehicles, deep learning approaches are at the forefront of so many domains. Deep learning mode…
Perceptual Loss for Robust Unsupervised Homography Estimation
Daniel Koguciuk, Elahe Arani, Bahram Zonooz
Homography estimation is often an indispensable step in many computer vision tasks. The existing approaches, however, are not robust to illumination and/or larger viewpoint changes…
Distill on the Go: Online knowledge distillation in self-supervised learning
Prashant Bhat, Elahe Arani, Bahram Zonooz
Self-supervised learning solves pretext prediction tasks that do not require annotations to learn feature representations. For vision tasks, pretext tasks such as predicting rotati…
Noisy Concurrent Training for Efficient Learning under Label Noise
Fahad Sarfraz, Elahe Arani, Bahram Zonooz
Deep neural networks (DNNs) fail to learn effectively under label noise and have been shown to memorize random labels which affect their generalization performance. We consider lea…
Adversarial Concurrent Training: Optimizing Robustness and Accuracy Trade-off of Deep Neural Networks
Elahe Arani, Fahad Sarfraz, Bahram Zonooz
Adversarial training has been proven to be an effective technique for improving the adversarial robustness of models. However, there seems to be an inherent trade-off between optim…
Monocular Vision based Crowdsourced 3D Traffic Sign Positioning with Unknown Camera Intrinsics and Distortion Coefficients
Hemang Chawla, Matti Jukola, Elahe Arani +1
Autonomous vehicles and driver assistance systems utilize maps of 3D semantic landmarks for improved decision making. However, scaling the mapping process as well as regularly upda…