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 …
On the unreasonable vulnerability of transformers for image restoration-and an easy fix
Following their success in visual recognition tasks, Vision Transformers (ViTs) are being
increasingly employed for image restoration. As a few recent works claim that ViTs for image …
increasingly employed for image restoration. As a few recent works claim that ViTs for image …
Reasons for the superiority of stochastic estimators over deterministic ones: Robustness, consistency and perceptual quality
Stochastic restoration algorithms allow to explore the space of solutions that correspond to
the degraded input. In this paper we reveal additional fundamental advantages of stochastic …
the degraded input. In this paper we reveal additional fundamental advantages of stochastic …
Transfer CLIP for Generalizable Image Denoising
Image denoising is a fundamental task in computer vision. While prevailing deep learning-
based supervised and self-supervised methods have excelled in eliminating in-distribution …
based supervised and self-supervised methods have excelled in eliminating in-distribution …
Towards robustifying image classifiers against the perils of adversarial attacks on artificial intelligence systems
T Anastasiou, S Karagiorgou, P Petrou… - Sensors, 2022 - mdpi.com
Adversarial machine learning (AML) is a class of data manipulation techniques that cause
alterations in the behavior of artificial intelligence (AI) systems while going unnoticed by …
alterations in the behavior of artificial intelligence (AI) systems while going unnoticed by …
Synergy-of-experts: Collaborate to improve adversarial robustness
Learning adversarially robust models require invariant predictions to a small neighborhood
of its natural inputs, often encountering insufficient model capacity. There is research …
of its natural inputs, often encountering insufficient model capacity. There is research …
Leveraging AutoEncoders and chaos theory to improve adversarial example detection
The phenomenon of adversarial examples is one of the most attractive topics in machine
learning research these days. These are particular cases that are able to mislead neural …
learning research these days. These are particular cases that are able to mislead neural …
Learning to Translate Noise for Robust Image Denoising
Deep learning-based image denoising techniques often struggle with poor generalization
performance to out-of-distribution real-world noise. To tackle this challenge, we propose a …
performance to out-of-distribution real-world noise. To tackle this challenge, we propose a …
A Diffusion Equation for Improving the Robustness of Deep Learning Speckle Removal Model
Speckle removal aims to smooth noise while preserving image boundaries and texture
information. In recent years, speckle removal models based on deep learning methods have …
information. In recent years, speckle removal models based on deep learning methods have …
[HTML][HTML] Complementary Transformer Network for cross-scale single image denoising
M Zhang, X Liu, H Liu, J Hu - Alexandria Engineering Journal, 2024 - Elsevier
Cliffside carving images are often affected by various types of noise, such as uneven
lighting, shadows, dust, and weathering, which impair the clarity and detail of the images …
lighting, shadows, dust, and weathering, which impair the clarity and detail of the images …