Expert Training: Enhancing AI Resilience to Image Coding Artifacts - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Expert Training: Enhancing AI Resilience to Image Coding Artifacts

Résumé

In the Machine-to-Machine (M2M) transmission context, there is a great need to reduce the amount of transmitted information using lossy compression. However, commonly used image compression methods are designed for human perception, not for Artificial Intelligence (AI) algorithms performances. It is known that these compression distortions affect many deep learning based architectures on several computer vision tasks. In this paper, we focus on the classification task and propose a new approach, named expert training, to enhance Convolutional Neural Networks (CNNs) resilience to compression distortions. We validated our approach using MnasNet and ResNet50 architectures, against image compression distortions introduced by three commonly used methods (JPEG, J2K and BPG), on the ImageNet dataset. The results showed a better robustness of these two architectures against the tested coding artifacts using the proposed expert training approach. Our code is publicly available at https://github.com/albmarie/expert training.
Fichier principal
Vignette du fichier
IPAS_22_HAL.pdf (1.28 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03555716 , version 1 (03-02-2022)

Identifiants

  • HAL Id : hal-03555716 , version 1

Citer

Alban Marie, Karol Desnos, Luce Morin, Lu Zhang. Expert Training: Enhancing AI Resilience to Image Coding Artifacts. Electronic Imaging, Image Processing: Algorithms and Systems XX, Jan 2022, San Francisco, United States. ⟨hal-03555716⟩
115 Consultations
116 Téléchargements

Partager

Gmail Facebook X LinkedIn More