User profiles for Bahram Zonooz

Bahram Zonooz

Eindhoven University of Technology
Verified email at tue.nl
Cited by 544

[HTML][HTML] Spectral weighting underlies perceived sound elevation

B Zonooz, E Arani, KP Körding, PATR Aalbers… - Scientific reports, 2019 - nature.com
The brain estimates the two-dimensional direction of sounds from the pressure-induced
displacements of the eardrums. Accurate localization along the horizontal plane (azimuth angle) …

Distill on the go: Online knowledge distillation in self-supervised learning

P Bhat, E Arani, B Zonooz - … of the IEEE/CVF Conference on …, 2021 - openaccess.thecvf.com
Self-supervised representation learning solves pretext prediction tasks that do not require
labeled data to learn feature representations. For vision tasks, pretext tasks such as predicting …

Learning fast, learning slow: A general continual learning method based on complementary learning system

E Arani, F Sarfraz, B Zonooz - arXiv preprint arXiv:2201.12604, 2022 - arxiv.org
Humans excel at continually learning from an ever-changing environment whereas it
remains a challenge for deep neural networks which exhibit catastrophic forgetting. The …

Transformers in self-supervised monocular depth estimation with unknown camera intrinsics

A Varma, H Chawla, B Zonooz, E Arani - arXiv preprint arXiv:2202.03131, 2022 - arxiv.org
The advent of autonomous driving and advanced driver assistance systems necessitates
continuous developments in computer vision for 3D scene understanding. Self-supervised …

Birt: Bio-inspired replay in vision transformers for continual learning

K Jeeveswaran, P Bhat, B Zonooz, E Arani - arXiv preprint arXiv …, 2023 - arxiv.org
The ability of deep neural networks to continually learn and adapt to a sequence of tasks has
remained challenging due to catastrophic forgetting of previously learned tasks. Humans, …

A comprehensive study of real-time object detection networks across multiple domains: A survey

…, O Magdy, S Kathiresan, B Zonooz - arXiv preprint arXiv …, 2022 - arxiv.org
Deep neural network based object detectors are continuously evolving and are used in a
multitude of applications, each having its own set of requirements. While safety-critical …

Knowledge distillation beyond model compression

F Sarfraz, E Arani, B Zonooz - 2020 25th International …, 2021 - ieeexplore.ieee.org
Knowledge distillation (KD) is commonly deemed as an effective model compression
technique in which a compact model (student) is trained under the supervision of a larger …

Perceptual loss for robust unsupervised homography estimation

D Koguciuk, E Arani, B Zonooz - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
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. …

Rgpnet: A real-time general purpose semantic segmentation

…, S Marzban, A Pata, B Zonooz - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
We propose a real-time general purpose semantic segmentation architecture, RGPNet, which
achieves significant performance gain in complex environments. RGPNet consists of a light…

Lsfsl: Leveraging shape information in few-shot learning

…, S Gowda, E Arani, B Zonooz - Proceedings of the …, 2023 - openaccess.thecvf.com
Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using
fewer samples, analogous to how humans learn from limited experience. In this limited-data …