Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912346301005824 |
|---|---|
| author | Vasilescu, Vlad Neacsu, Ana Faur, Daniela |
| author_facet | Vasilescu, Vlad Neacsu, Ana Faur, Daniela |
| contents | Single-image dehazing is an important topic in remote sensing applications, enhancing the quality of acquired images and increasing object detection precision. However, the reliability of such structures has not been sufficiently analyzed, which poses them to the risk of imperceptible perturbations that can significantly hinder their performance. In this work, we show that state-of-the-art image-to-image dehazing transformers are susceptible to adversarial noise, with even 1 pixel change being able to decrease the PSNR by as much as 2.8 dB. Next, we propose two lightweight fine-tuning strategies aimed at increasing the robustness of pre-trained transformers. Our methods results in comparable clean performance, while significantly increasing the protection against adversarial data. We further present their applicability in two remote sensing scenarios, showcasing their robust behavior for out-of-distribution data. The source code for adversarial fine-tuning and attack algorithms can be found at github.com/Vladimirescu/RobustDehazing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17829 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing Vasilescu, Vlad Neacsu, Ana Faur, Daniela Computer Vision and Pattern Recognition Artificial Intelligence Single-image dehazing is an important topic in remote sensing applications, enhancing the quality of acquired images and increasing object detection precision. However, the reliability of such structures has not been sufficiently analyzed, which poses them to the risk of imperceptible perturbations that can significantly hinder their performance. In this work, we show that state-of-the-art image-to-image dehazing transformers are susceptible to adversarial noise, with even 1 pixel change being able to decrease the PSNR by as much as 2.8 dB. Next, we propose two lightweight fine-tuning strategies aimed at increasing the robustness of pre-trained transformers. Our methods results in comparable clean performance, while significantly increasing the protection against adversarial data. We further present their applicability in two remote sensing scenarios, showcasing their robust behavior for out-of-distribution data. The source code for adversarial fine-tuning and attack algorithms can be found at github.com/Vladimirescu/RobustDehazing. |
| title | Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.17829 |