Advances in adversarial attacks and defenses in computer vision: A survey
Deep Learning is the most widely used tool in the contemporary field of computer vision. Its
ability to accurately solve complex problems is employed in vision research to learn deep …
ability to accurately solve complex problems is employed in vision research to learn deep …
A review on Single Image Super Resolution techniques using generative adversarial network
K Singla, R Pandey, U Ghanekar - Optik, 2022 - Elsevier
Abstract Single Image Super Resolution (SISR) is a process to obtain a high pixel density
and refined details from a low resolution (LR) image to get upscaled and sharper high …
and refined details from a low resolution (LR) image to get upscaled and sharper high …
Threat of adversarial attacks on deep learning in computer vision: A survey
Deep learning is at the heart of the current rise of artificial intelligence. In the field of
computer vision, it has become the workhorse for applications ranging from self-driving cars …
computer vision, it has become the workhorse for applications ranging from self-driving cars …
Towards robust rain removal against adversarial attacks: A comprehensive benchmark analysis and beyond
Rain removal aims to remove rain streaks from images/videos and reduce the disruptive
effects caused by rain. It not only enhances image/video visibility but also allows many …
effects caused by rain. It not only enhances image/video visibility but also allows many …
Learning loss for test-time augmentation
Data augmentation has been actively studied for robust neural networks. Most of the recent
data augmentation methods focus on augmenting datasets during the training phase. At the …
data augmentation methods focus on augmenting datasets during the training phase. At the …
Physics-driven turbulence image restoration with stochastic refinement
Image distortion by atmospheric turbulence is a stochastic degradation, which is a critical
problem in long-range optical imaging systems. A number of research has been conducted …
problem in long-range optical imaging systems. A number of research has been conducted …
Fast certified robust training with short warmup
Recently, bound propagation based certified robust training methods have been proposed
for training neural networks with certifiable robustness guarantees. Despite that state-of-the …
for training neural networks with certifiable robustness guarantees. Despite that state-of-the …
First earth-imaging CubeSat with harmonic diffractive lens
N Ivliev, V Evdokimova, V Podlipnov, M Petrov… - Remote Sensing, 2022 - mdpi.com
Launched in March 2021, the 3U CubeSat nanosatellite was the first ever to use an ultra-
lightweight harmonic diffractive lens for Earth remote sensing. We describe the CubeSat …
lightweight harmonic diffractive lens for Earth remote sensing. We describe the CubeSat …
Learning provably robust estimators for inverse problems via jittering
A Krainovic, M Soltanolkotabi… - Advances in Neural …, 2024 - proceedings.neurips.cc
Deep neural networks provide excellent performance for inverse problems such as
denoising. However, neural networks can be sensitive to adversarial or worst-case …
denoising. However, neural networks can be sensitive to adversarial or worst-case …
Robust single image reflection removal against adversarial attacks
This paper addresses the problem of robust deep single-image reflection removal (SIRR)
against adversarial attacks. Current deep learning based SIRR methods have shown …
against adversarial attacks. Current deep learning based SIRR methods have shown …