research
∙
03/24/2022
Token Dropping for Efficient BERT Pretraining
Transformer-based models generally allocate the same amount of computati...
share
research
∙
02/24/2022
Auto-scaling Vision Transformers without Training
This work targets automated designing and scaling of Vision Transformers...
research
∙
12/17/2021
A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation
This work presents a simple vision transformer design as a strong baseli...
research
∙
10/08/2021
Speeding up Deep Model Training by Sharing Weights and Then Unsharing
We propose a simple and efficient approach for training the BERT model. ...
research
∙
01/29/2021
A new communication paradigm: from bit accuracy to semantic fidelity
Wireless communication has achieved great success in the past several de...
research
∙
10/22/2020
Efficient Scale-Permuted Backbone with Learned Resource Distribution
Recently, SpineNet has demonstrated promising results on object detectio...
research
∙
04/06/2020
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
Natural Language Processing (NLP) has recently achieved great success by...
research
∙
03/24/2020
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
Neural architecture search (NAS) has shown promising results discovering...
research
∙
12/10/2019
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
Convolutional neural networks typically encode an input image into a ser...
research
∙
09/06/2019
High Resolution Medical Image Analysis with Spatial Partitioning
Medical images such as 3D computerized tomography (CT) scans and patholo...
research
∙
04/01/2019
Reducing BERT Pre-Training Time from 3 Days to 76 Minutes
Large-batch training is key to speeding up deep neural network training ...
research
∙
05/16/2018