Learning to Generate Training Datasets for Robust Semantic Segmentation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Learning to Generate Training Datasets for Robust Semantic Segmentation

Résumé

Semantic segmentation techniques have shown significant progress in recent years, but their robustness to real-world perturbations and data samples not seen during training remains a challenge, particularly in safety-critical applications. In this paper, we propose a novel approach to improve the robustness of semantic segmentation techniques by leveraging the synergy between label-to-image generators and image-to-label segmentation models. Specifically, we design and train Robusta, a novel robust conditional generative adversarial network to generate realistic and plausible perturbed or outlier images that can be used to train reliable segmentation models. We conduct in-depth studies of the proposed generative model, assess the performance and robustness of the downstream segmentation network, and demonstrate that our approach can significantly enhance the robustness of semantic segmentation techniques in the face of real-world perturbations, distribution shifts, and out-of-distribution samples. Our results suggest that this approach could be valuable in safety-critical applications, where the reliability of semantic segmentation techniques is of utmost importance and comes with a limited computational budget in inference. We will release our code shortly.
Fichier non déposé

Dates et versions

hal-04321102 , version 1 (04-12-2023)

Identifiants

  • HAL Id : hal-04321102 , version 1

Citer

Marwane Hariat, Olivier Laurent, Rémi Kazmierczak, Andrei Bursuc, Angela Yao, et al.. Learning to Generate Training Datasets for Robust Semantic Segmentation. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2024, WAIKOLOA, United States. ⟨hal-04321102⟩
31 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More