28 citations · 35 across the 5 of their papers we have counts for
5 papers
QShield: Securing Neural Networks Against Adversarial Attacks using Quantum Circuits
Navid Azimi, Aditya Prakash, Yao Wang +1
Deep neural networks remain highly vulnerable to adversarial perturbations, limiting their reliability in security- and safety-critical applications. To address this challenge, we…
PAM: Understanding Product Images in Cross Product Category Attribute Extraction
Rongmei Lin, Xiang He, Jie Feng +4
Understanding product attributes plays an important role in improving online shopping experience for customers and serves as an integral part for constructing a product knowledge g…
Learning with Hyperspherical Uniformity
Weiyang Liu, Rongmei Lin, Zhen Liu +3
Due to the over-parameterization nature, neural networks are a powerful tool for nonlinear function approximation. In order to achieve good generalization on unseen data, a suitabl…
Orthogonal Over-Parameterized Training
Weiyang Liu, Rongmei Lin, Zhen Liu +5
The inductive bias of a neural network is largely determined by the architecture and the training algorithm. To achieve good generalization, how to effectively train a neural netwo…
Regularizing Neural Networks via Minimizing Hyperspherical Energy
Rongmei Lin, Weiyang Liu, Zhen Liu +5
Inspired by the Thomson problem in physics where the distribution of multiple propelling electrons on a unit sphere can be modeled via minimizing some potential energy, hyperspheri…