Amin Ghiasi

Publication Activity (10 Years)

Years Active: 2019-2023
Publications (10 Years): 19

Top Topics

Semantically Meaningful

Visual Exploration

Graph Transduction

Knowledge Transfer

Top Venues

Publications

Amin Ghiasi, Ali Shafahi, Reza Ardekani
Improving Robustness with Adaptive Weight Decay. NeurIPS (2023)
Amin Ghiasi, Hamid Kazemi, Steven Reich, Chen Zhu, Micah Goldblum, Tom Goldstein
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations. CoRR (2022)
Amin Ghiasi, Hamid Kazemi, Eitan Borgnia, Steven Reich, Manli Shu, Micah Goldblum, Andrew Gordon Wilson, Tom Goldstein
What do Vision Transformers Learn? A Visual Exploration. CoRR (2022)
Avi Schwarzschild, Arjun Gupta, Amin Ghiasi, Micah Goldblum, Tom Goldstein
The Uncanny Similarity of Recurrence and Depth. ICLR (2022)
Amin Ghiasi, Ali Shafahi, Reza Ardekani
Adaptive Weight Decay: On The Fly Weight Decay Tuning for Improving Robustness. CoRR (2022)
Amin Ghiasi, Hamid Kazemi, Steven Reich, Chen Zhu, Micah Goldblum, Tom Goldstein
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations. ICML (2022)
Eitan Borgnia, Valeriia Cherepanova, Liam Fowl, Amin Ghiasi, Jonas Geiping, Micah Goldblum, Tom Goldstein, Arjun Gupta
Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff. ICASSP (2021)
Amin Ghiasi, Masoud Seddighin
Approximate Competitive Equilibrium with Generic Budget. SAGT (2021)
Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam Fowl, Arjun Gupta, Amin Ghiasi, Furong Huang, Micah Goldblum, Tom Goldstein
DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations. CoRR (2021)
Amin Ghiasi, Ali Shafahi, Tom Goldstein
Breaking Certified Defenses: Semantic Adversarial Examples with Spoofed robustness Certificates. ICLR (2020)
Amin Ghiasi, Ali Shafahi, Tom Goldstein
Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates. CoRR (2020)
Chen Zhu, Zheng Xu, Ali Shafahi, Manli Shu, Amin Ghiasi, Tom Goldstein
Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer. CoRR (2020)
Ali Shafahi, Parsa Saadatpanah, Chen Zhu, Amin Ghiasi, Christoph Studer, David W. Jacobs, Tom Goldstein
Adversarially robust transfer learning. ICLR (2020)
Eitan Borgnia, Valeriia Cherepanova, Liam Fowl, Amin Ghiasi, Jonas Geiping, Micah Goldblum, Tom Goldstein, Arjun Gupta
Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff. CoRR (2020)
Ali Shafahi, Amin Ghiasi, Furong Huang, Tom Goldstein
Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training? CoRR (2019)
Ali Shafahi, Parsa Saadatpanah, Chen Zhu, Amin Ghiasi, Christoph Studer, David W. Jacobs, Tom Goldstein
Adversarially robust transfer learning. CoRR (2019)
Ali Shafahi, Mahyar Najibi, Amin Ghiasi, Zheng Xu, John P. Dickerson, Christoph Studer, Larry S. Davis, Gavin Taylor, Tom Goldstein
Adversarial Training for Free! CoRR (2019)
Ali Shafahi, Mahyar Najibi, Amin Ghiasi, Zheng Xu, John P. Dickerson, Christoph Studer, Larry S. Davis, Gavin Taylor, Tom Goldstein
Adversarial training for free! NeurIPS (2019)
Ali Shafahi, Amin Ghiasi, Mahyar Najibi, Furong Huang, John P. Dickerson, Tom Goldstein
Batch-wise Logit-Similarity: Generalizing Logit-Squeezing and Label-Smoothing. BMVC (2019)