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

Adversarial contrastive learning (ACL) is considered an effective way to improve the robustness of pre-trained models. In contrastive learning, a projector which consists of multilayer perceptron (MLP) will project high dimension 3D point cloud feature into low dimension for calculating contrastive loss during contrastive pertaining. We introduce a new method to generate high-quality 3D adversarial examples for adversarial training by utilizing virtual adversarial loss with the feature representations before projector 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 state-of-the-art result in robust accuracy over other contrastive adversarial learning methods.