activity
20182021
most citedMobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices

94 citations · 102 across the 3 of their papers we have counts for

collaborators

9 papers

cs.LG20213 cited

Speeding up Deep Model Training by Sharing Weights and Then Unsharing

Shuo Yang, Le Hou, Xiaodan Song +2

We propose a simple and efficient approach for training the BERT model. Our approach exploits the special structure of BERT that contains a stack of repeated modules (i.e., transfo…

cs.CV2020

Efficient Scale-Permuted Backbone with Learned Resource Distribution

Xianzhi Du, Tsung-Yi Lin, Pengchong Jin +4

Recently, SpineNet has demonstrated promising results on object detection and image classification over ResNet model. However, it is unclear if the improvement adds up when combini…

cs.LG20205 cited

Go Wide, Then Narrow: Efficient Training of Deep Thin Networks

Denny Zhou, Mao Ye, Chen Chen +6

For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is…

cs.CL202094 cited

MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices

Zhiqing Sun, Hongkun Yu, Xiaodan Song +3

Natural Language Processing (NLP) has recently achieved great success by using huge pre-trained models with hundreds of millions of parameters. However, these models suffer from he…

cs.CV2020

BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models

Jiahui Yu, Pengchong Jin, Hanxiao Liu +7

Neural architecture search (NAS) has shown promising results discovering models that are both accurate and fast. For NAS, training a one-shot model has become a popular strategy to…

cs.CV2019

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

Xianzhi Du, Tsung-Yi Lin, Pengchong Jin +5

Convolutional neural networks typically encode an input image into a series of intermediate features with decreasing resolutions. While this structure is suited to classification t…