Universal robustness via median randomized smoothing for real-world super resolution - CEA - Université Paris-Saclay Accéder directement au contenu
Autre Publication Scientifique Année : 2024

Universal robustness via median randomized smoothing for real-world super resolution

Robustesse universelle par lissage aléatoire médian pour la super-résolution dans le monde réel

Résumé

Most of the recent literature on image Super-Resolution (SR) can be classified into two main approaches. The first one involves learning a corruption model tailored to a specific dataset, aiming to mimic the noise and corruption in low-resolution images, such as sensor noise. However, this approach is data-specific, tends to lack adaptability, and its accuracy diminishes when faced with unseen types of image corruptions. A second and more recent approach, referred to as Robust Super-Resolution (RSR), proposes to improve real-world SR by harnessing the generalization capabilities of a model by making it robust to adversarial attacks. To delve further into this second approach, our paper explores the universality of various methods for enhancing the robustness of deep learning SR models. In other words, we inquire: "Which robustness method exhibits the highest degree of adaptability when dealing with a wide range of adversarial attacks ?". Our extensive experimentation on both synthetic and real-world images empirically demonstrates that median randomized smoothing (MRS) is more general in terms of robustness compared to adversarial learning techniques, which tend to focus on specific types of attacks. Furthermore, as expected, we also illustrate that the proposed universal robust method enables the SR model to handle standard corruptions more effectively, such as blur and Gaussian noise, and notably, corruptions naturally present in real-world images. These results support the significance of shifting the paradigm in the development of real-world SR methods towards RSR, especially via MRS.
Fichier principal
Vignette du fichier
Certfication_for_Super_Resolution.pdf (7.98 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04611279 , version 1 (13-06-2024)

Licence

Identifiants

Citer

Zakariya Chaouai, Mohamed Tamaazousti. Universal robustness via median randomized smoothing for real-world super resolution. 2024, ⟨10.48550/arXiv.2405.14934⟩. ⟨hal-04611279⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More