activity
20172023
most citedLearning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization

26 citations · 66 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG20206 cited

WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic

Renkun Ni, Hong-min Chu, Oscar Castañeda +3

Low-resolution neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity. Nonetheless, these products are accumulated…

cs.CR2020

Certified Defenses for Adversarial Patches

Ping-Yeh Chiang, Renkun Ni, Ahmed Abdelkader +3

Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems. This paper studies certified and empirical defenses against…

cs.LG20206 cited

Improving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers

Chen Zhu, Renkun Ni, Ping-yeh Chiang +3

Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical…

cs.LG2020

Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks

Micah Goldblum, Steven Reich, Liam Fowl +3

Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods,…

cs.LG2019

WITCHcraft: Efficient PGD attacks with random step size

Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum +4

State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points. Iterative FGSM-based methods wit…

cs.CV201726 cited

Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization

Yinpeng Dong, Renkun Ni, Jianguo Li +3

Low-bit deep neural networks (DNNs) become critical for embedded applications due to their low storage requirement and computing efficiency. However, they suffer much from the non-…