Denoising Masked AutoEncoders Help Robust Classification

1 code implementation • 10 Oct 2022 • Quanlin Wu, Hang Ye, Yuntian Gu, Huishuai Zhang, LiWei Wang, Di He

In this paper, we propose a new self-supervised method, which is called Denoising Masked AutoEncoders (DMAE), for learning certified robust classifiers of images.

Classification Denoising +1

Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection

1 code implementation • 22 Jul 2022 • Hang Ye, Wentao Zhu, Chunyu Wang, Rujie Wu, Yizhou Wang

While the voxel-based methods have achieved promising results for multi-person 3D pose estimation from multi-cameras, they suffer from heavy computation burdens, especially for large scenes.

3D Multi-Person Pose Estimation 3D Pose Estimation

Guided Diffusion Model for Adversarial Purification from Random Noise

no code implementations • 22 Jun 2022 • Quanlin Wu, Hang Ye, Yuntian Gu

In this paper, we propose a novel guided diffusion purification approach to provide a strong defense against adversarial attacks.