top of page

This site was designed with the

website builder. Create your website today.Start Now

Senior Lecturer (Assistant Professor)
Faculty of Engineering

Bar-Ilan University

Tom Tirer

Research

My research interests are in the fields of signal and image processing, machine learning, optimization, and their interconnections.

My lines of research include (but not limited to):

Solving inverse problems (e.g., super-resolution, inpainting, etc.) using deep data-driven priors (e.g., denoisers, GANs, and diffusion models)
Exploring the evolution of features in deep neural networks (e.g., various strategies for analyzing and experimenting neural collapse of overtrained classifiers)
Developing efficient optimization frameworks for signal recovery and parameter estimation, and analyzing their convergence / performance

I'm looking for self-motivated graduate students with strong academic record that are interested in doing research on theory and applications in these fields. If you are interested, you are more than welcome to send me an email with your CV and academic record so I can understand your background.

Team

tirer dot tom at gmail dot com

Publication

Publications

K. Rahimi, T. Tirer, and O. Lindenbaum “Multiple Descents in Unsupervised Learning: The Role of Noise, Domain Shift and Anomalies,” Submitted, 2024.

V. Kothapalli and T. Tirer, “Kernel vs. Kernel: Exploring How the Data Structure Affects Neural Collapse,” Submitted, 2024.

[article] [code]

L. Dabah and T. Tirer, “On Calibration and Conformal Prediction of Deep Classifiers,”

Submitted, 2024.

T. Garber and T. Tirer, “Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance,” Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[article] [code] [video] [poster]

T. Tirer, R. Giryes, S. Y. Chun, and Y. C. Eldar, “Deep Internal Learning: Deep Learning from a Single Input,” Accepted to IEEE Signal Processing Magazine, 2024.

V. Kothapalli, T. Tirer, and J. Bruna, “A Neural Collapse Perspective on Feature Evolution in Graph
Neural Networks,” Conference on Neural Information Processing Systems (NeurIPS), 2023.

[article] [code] [slides]

S. Abu Hussein, T. Tirer, and R. Giryes, “ADIR: Adaptive Diffusion for Image Reconstruction,”
Submitted, 2022.

[article] [website]

T. Tirer*, H. Huang*, and J. Niles-Weed, “Perturbation Analysis of Neural Collapse,”
International Conference on Machine Learning (ICML), 2023.

[article] [slides] [video] [poster]

O. Bialer and T. Tirer, “Performance Analysis of Automotive SAR with Radar Based Motion Estimation,” IEEE Transactions on Vehicular Technology, vol. 72, no. 9, pp. 11332–11345, 2023.

J. Shani, T. Tirer, R. Giryes, and T. Bendory, “Denoiser-Based projections for 2D Super-Resolution Multi-Reference Alignment,” IEEE Open Journal of Signal Processing, vol. 5, pp. 621–629, 2024.

T. Tirer and J. Bruna, “Extended Unconstrained Features Model for Exploring Deep Neural Collapse,”
International Conference on Machine Learning (ICML), 2022.

[article] [video]

T. Tirer and O. Bialer, “Direction of Arrival Estimation and Phase-Correction for Non-Coherent Sub-Arrays: A Convex Optimization Approach,” IEEE Transactions on Aerospace and Electronic Systems, vol. 58, no. 6, pp. 5571–5585, 2022.

T. Tirer and R. Giryes, “On the Convergence Rate of Projected Gradient Descent for a Back-Projection based Objective,” SIAM Journal on Imaging Sciences (SIIMS), vol. 14, no. 4, pp. 1504–1531, 2021.

S. Abu Hussein, T. Tirer, S. Y. Chun, Y. C. Eldar, and R. Giryes, “Image Restoration by Deep Projected GSURE,” Winter Conference on Applications of Computer Vision (WACV), 2022.

[article] [code]

O. Bialer, A. Jonas, and T. Tirer, “Code Optimization for Fast Chirp FMCW Automotive MIMO Radar,”
IEEE Transactions on Vehicular Technology, vol. 70, no. 8, pp. 7582–7593, 2021.

O. Bialer, A. Jonas, and T. Tirer, “Super Resolution Wide Aperture Automotive Radar,”
IEEE Sensors Journal, vol. 21, no. 16, pp. 17846–17858, 2021.

[article] [Prototype]

T. Tirer, J. Bruna, and R. Giryes, “Kernel-Based Smoothness Analysis of Residual Networks,”
Mathematical and Scientific Machine Learning (MSML), 2021.

[article] [code]

T. Tirer and O. Bialer, “A Method for Reducing the Performance Gap Between Non-Coherent and Coherent Sub-Arrays,” IEEE Transactions on Signal Processing, vol. 68, no. 1, pp. 3358–3370, 2020.

[pdf] [code - email me]

S. Abu Hussein, T. Tirer, and R. Giryes, “Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-Resolvers,” Conf. on Computer Vision and Pattern Recog. (CVPR) 2020 (oral).

[article] [code]

T. Tirer and R. Giryes, “Back-Projection based Fidelity Term for Ill-Posed Linear Inverse Problems,”
IEEE Transactions on Image Processing, vol. 29, no. 1, pp. 6164–6179, 2020.

[article] [code] ([slides] [video] [longer video] include IDBP and IAGAN)

S. Abu Hussein*, T. Tirer*, and R. Giryes, “Image-Adaptive GAN based Reconstruction,”
AAAI Conference on Artificial Intelligence, 2020. (*Equal contributors)

[article] [code]

T. Tirer and R. Giryes, “Super-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning,” IEEE Signal Processing Letters, vol. 26, no. 7, pp. 1080–1084, 2019.

[article] [code]

T. Tirer and R. Giryes, “Image Restoration by Iterative Denoising and Backward Projections”,
IEEE Transactions on Image Processing, vol. 28, no. 3, pp. 1220–1234, 2019.

[article] [code] [slides]

T. Tirer and R. Giryes, “Generalizing CoSaMP to Signals from a Union of Low Dimensional Linear Subspaces”, Accepted to Applied and Computational Harmonic Analysis, 2018.

[article] [code] [poster (SPARS17)]

T. Tirer and A.J. Weiss, “High Resolution Localization of Narrowband Radio Emitters Based on Doppler Frequency Shifts,” Signal Processing (Elsevier), vol. 141, pp. 288 - 298, Dec. 2017.

T. Tirer and A.J. Weiss, “Performance Analysis of a High-Resolution Direct Position Determination Method,” IEEE Transactions on Signal Processing, vol. 65, no. 3, pp. 544 - 554, Feb. 2017.

T. Tirer and A.J. Weiss, “High Resolution Direct Position Determination of Radio Frequency Sources,” IEEE Signal Processing Letters, vol. 23, no. 2, pp. 192 - 196, Feb. 2016.

[article] [code]

Conferences of up to 5 pages

T. Tirer, “Iteratively Preconditioned Guidance of Denoising (Diffusion) Models for Image Restoration,” IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2024

E. Yogev-Ofer, T. Tirer, and R. Giryes, “An Interpretation of Regularization by Denoising and its Application with the Back-Projected Fidelity Term,” IEEE Int. Conf. on Image Processing (ICIP), 2021.

O. Bialer, A. Jonas, and T. Tirer, “Code Design for Automotive MIMO Radar,”
European Signal Processing Conference (EUSIPCO), 2021.

T. Tirer and O. Bialer, “Direction of Arrival Estimation for Non-Coherent Sub-Arrays via Joint Sparse and Low-Rank Signal Recovery,” IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2021

J. Zukerman, T. Tirer, and R. Giryes, “BP-DIP: A Backprojection based Deep Image Prior,”
European Signal Processing Conference (EUSIPCO), 2020.

[article] [code]

T. Tirer and O. Bialer, “Effective Approximate Maximum Likelihood Estimation of Angles of Arrival for Non-Coherent Sub-Arrays,” IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2020

O. Bialer, N. Garnett, and T. Tirer, “Performance Advantages of Deep Neural Networks for Angle of Arrival Estimation,” IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2019

T. Tirer and R. Giryes, “Task-Driven Dictionary Learning based on Convolutional Neural Network Features,” European Signal Processing Conference (EUSIPCO), 2018.

T. Tirer and R. Giryes, “An Iterative Denoising and Backwards Projections Method and its Advantages for Blind Deblurring,” IEEE International Conference on Image Processing (ICIP), 2018.

Other (hopefully helpful) stuff

Short review of optimization methods for deep learning, TAU course, 2018

bottom of page