activity
20182022
most citedBridging Mode Connectivity in Loss Landscapes and Adversarial Robustness

33 citations · 51 across the 9 of their papers we have counts for

collaborators

16 papers

cs.LG2022

Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed

Hao Cheng, Pu Zhao, Yize Li +4

Recently, Diffenderfer and Kailkhura proposed a new paradigm for learning compact yet highly accurate binary neural networks simply by pruning and quantizing randomly weighted full…

cs.CV2021

Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search

Pu Zhao, Wei Niu, Geng Yuan +4

Object detection plays an important role in self-driving cars for security development. However, mobile systems on self-driving cars with limited computation resources lead to diff…

cs.LG2021

A Compression-Compilation Framework for On-mobile Real-time BERT Applications

Wei Niu, Zhenglun Kong, Geng Yuan +7

Transformer-based deep learning models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. In this paper, we propose a compression-compila…

cs.LG2021

High-Robustness, Low-Transferability Fingerprinting of Neural Networks

Siyue Wang, Xiao Wang, Pin-Yu Chen +2

This paper proposes Characteristic Examples for effectively fingerprinting deep neural networks, featuring high-robustness to the base model against model pruning as well as low-tr…

cs.CV20205 cited

Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device

Pu Zhao, Wei Niu, Geng Yuan +7

3D object detection is an important task, especially in the autonomous driving application domain. However, it is challenging to support the real-time performance with the limited…

cs.LG2020

NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration

Zhengang Li, Geng Yuan, Wei Niu +13

With the increasing demand to efficiently deploy DNNs on mobile edge devices, it becomes much more important to reduce unnecessary computation and increase the execution speed. Pri…