Evaluation of Image Quality Assessment Metrics for Semantic Segmentation in a Machine-to-Machine Communication Scenario - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Evaluation of Image Quality Assessment Metrics for Semantic Segmentation in a Machine-to-Machine Communication Scenario

Résumé

Image and video compression aims at finding an optimal trade-off between rate and distortion. This is done through Rate-Distortion Optimization (RDO) in traditional encoders with the use of Image Quality Assessment (IQA) metrics. While it is known that most IQA metrics are designed to be correlated with human perception, there is no evidence that this observation can be generalized in a Video Coding for Machines (VCM) context, where the receiver is not a human anymore but a machine. In this paper, we propose an evaluation protocol to measure the correlation level between conventional Full-Reference (FR) IQA metrics and machine perception through the semantic segmentation vision task. Experiments showed a relatively low correlation between them when measured on the block-level. This observation implies the need of RDO algorithms that are better suited for Machine-to-Machine (M2M) communications. In order to facilitate the emergence of IQA metrics that better reflect machine perception, the code and dataset used to perform this study is made freely available at https://github.com/albmarie/iqa m2m segmentation.
Fichier principal
Vignette du fichier
QOMEX2023_HAL_update.pdf (11.27 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04091521 , version 1 (08-05-2023)
hal-04091521 , version 2 (18-07-2023)

Identifiants

Citer

Alban Marie, Karol Desnos, Luce Morin, Lu Zhang. Evaluation of Image Quality Assessment Metrics for Semantic Segmentation in a Machine-to-Machine Communication Scenario. 15th International Conference on Quality of Multimedia Experience (QoMEX), Jun 2023, Ghent, Belgium. pp.1-6, ⟨10.1109/QoMEX58391.2023.10178503⟩. ⟨hal-04091521v2⟩
134 Consultations
69 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More