no code implementations • ICCV 2021 • Omid Poursaeed, Tianxing Jiang, Harry Yang, Serge Belongie, SerNam Lim
Adversarial training with these examples enable the model to withstand a wide range of attacks by observing a variety of input alterations during training.
1 code implementation • 1 Aug 2020 • Omid Poursaeed, Tianxing Jiang, Han Qiao, Nayun Xu, Vladimir G. Kim
A point cloud can be rotated in infinitely many ways, which provides a rich label-free source for self-supervision.
Ranked #10 on 3D Point Cloud Linear Classification on ModelNet40
3D Point Cloud Linear Classification Self-Supervised Learning +1
no code implementations • 20 Nov 2019 • Omid Poursaeed, Tianxing Jiang, Yordanos Goshu, Harry Yang, Serge Belongie, Ser-Nam Lim
We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation.