Achieving robustness in classification using optimal transport with hinge regularization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Achieving robustness in classification using optimal transport with hinge regularization

Résumé

We propose a new framework for robust binary classification, with Deep Neural Networks, based on a hinge regularization of the Kantorovich-Rubinstein dual formulation for the estimation of the Wasserstein distance. The robustness of the approach is guaranteed by the strict Lipschitz constraint on functions required by the optimization problem and direct interpretation of the loss in terms of adversarial robustness. We prove that this classification formulation has a solution, and is still the dual formulation of an optimal transportation problem. We also establish the geometrical properties of this optimal solution. We summarize state-of-the-art methods to enforce Lipschitz constraints on neural networks and we propose new ones for convolutional networks (associated with an open source library for this purpose). The experiments show that the approach provides the expected guarantees in terms of robustness without any significant accuracy drop. The results also suggest that adversarial attacks on the proposed models visibly and meaningfully change the input, and can thus serve as an explanation for the classification.

Dates et versions

hal-03033400 , version 1 (01-12-2020)

Identifiants

Citer

Mathieu Serrurier, Franck Mamalet, Alberto González-Sanz, Thibaut Boissin, Jean-Michel Loubes, et al.. Achieving robustness in classification using optimal transport with hinge regularization. Conference on Computer Vision and Pattern Recognition, Jun 2021, Virtuel, Canada. ⟨10.1109/CVPR46437.2021.00057⟩. ⟨hal-03033400⟩
137 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More