User profiles for Bahram Zonooz
Bahram ZonoozEindhoven University of Technology Verified email at tue.nl Cited by 544 |
[HTML][HTML] Spectral weighting underlies perceived sound elevation
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) …
displacements of the eardrums. Accurate localization along the horizontal plane (azimuth angle) …
Distill on the go: Online knowledge distillation in self-supervised learning
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 …
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
Humans excel at continually learning from an ever-changing environment whereas it
remains a challenge for deep neural networks which exhibit catastrophic forgetting. The …
remains a challenge for deep neural networks which exhibit catastrophic forgetting. The …
Transformers in self-supervised monocular depth estimation with unknown camera intrinsics
The advent of autonomous driving and advanced driver assistance systems necessitates
continuous developments in computer vision for 3D scene understanding. Self-supervised …
continuous developments in computer vision for 3D scene understanding. Self-supervised …
Birt: Bio-inspired replay in vision transformers for continual learning
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, …
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 …
multitude of applications, each having its own set of requirements. While safety-critical …
Knowledge distillation beyond model compression
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 …
technique in which a compact model (student) is trained under the supervision of a larger …
Perceptual loss for robust unsupervised homography estimation
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. …
existing approaches, however, are not robust to illumination and/or larger viewpoint changes. …
Rgpnet: A real-time general purpose semantic segmentation
We propose a real-time general purpose semantic segmentation architecture, RGPNet, which
achieves significant performance gain in complex environments. RGPNet consists of a light…
achieves significant performance gain in complex environments. RGPNet consists of a light…
Lsfsl: Leveraging shape information in few-shot learning
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 …
fewer samples, analogous to how humans learn from limited experience. In this limited-data …