PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack

by   Junxuan Huang, et al.

Despite recent success of self-supervised based contrastive learning model for 3D point clouds representation, the adversarial robustness of such pre-trained models raised concerns. Adversarial contrastive learning (ACL) is considered an effective way to improve the robustness of pre-trained models. In contrastive learning, the projector is considered an effective component for removing unnecessary feature information during contrastive pretraining and most ACL works also use contrastive loss with projected feature representations to generate adversarial examples in pretraining, while "unprojected " feature representations are used in generating adversarial inputs during inference.Because of the distribution gap between projected and "unprojected" features, their models are constrained of obtaining robust feature representations for downstream tasks. We introduce a new method to generate high-quality 3D adversarial examples for adversarial training by utilizing virtual adversarial loss with "unprojected" feature representations in contrastive learning framework. We present our robust aware loss function to train self-supervised contrastive learning framework adversarially. Furthermore, we find selecting high difference points with the Difference of Normal (DoN) operator as additional input for adversarial self-supervised contrastive learning can significantly improve the adversarial robustness of the pre-trained model. We validate our method, PointACL on downstream tasks, including 3D classification and 3D segmentation with multiple datasets. It obtains comparable robust accuracy over state-of-the-art contrastive adversarial learning methods.


page 1

page 2

page 3

page 4


SCAT: Robust Self-supervised Contrastive Learning via Adversarial Training for Text Classification

Despite their promising performance across various natural language proc...

When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?

Contrastive learning (CL) can learn generalizable feature representation...

Towards Robust Graph Contrastive Learning

We study the problem of adversarially robust self-supervised learning on...

VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples

MoCo is effective for unsupervised image representation learning. In thi...

CLAWSAT: Towards Both Robust and Accurate Code Models

We integrate contrastive learning (CL) with adversarial learning to co-o...

Supervised Contrastive Prototype Learning: Augmentation Free Robust Neural Network

Transformations in the input space of Deep Neural Networks (DNN) lead to...

CoCoNets: Continuous Contrastive 3D Scene Representations

This paper explores self-supervised learning of amodal 3D feature repres...

Please sign up or login with your details

Forgot password? Click here to reset