1 code implementation • 30 Jul 2022 • Fanyou Wu, Yang Liu, Rado Gazo, Benes Bedrich, Xiaobo Qu
In the Amazon KDD Cup 2022, we aim to apply natural language processing methods to improve the quality of search results that can significantly enhance user experience and engagement with search engines for e-commerce.
no code implementations • 13 Nov 2020 • Fanyou Wu, Yang Liu, Zhiyuan Liu, Xiaobo Qu, Rado Gazo, Eva Haviarova
In our 2020 Competition solution, we further design multiple variants based on HR-NET and UNet.
1 code implementation • 7 Jun 2019 • Fanyou Wu, Rado Gazo, Eva Haviarova, Bedrich Benes
Consider $l_2$ norms attacks, Project Gradient Descent (PGD) and the Carlini and Wagner (C\&W) attacks are the two main methods, where PGD control max perturbation for adversarial examples while C\&W approach treats perturbation as a regularization term optimized it with loss function together.