Direct differentiable augmentation search
Data augmentation has been an indispensable tool to improve the performance of deep neural networks, however the augmentation can hardly transfer among different tasks and datasets. Consequently, a recent trend is to adopt AutoML technique to learn proper augmentation policy without extensive hand-c...
Saved in:
Main Authors: | LIU, Aoming, HUANG, Zehao, HUANG, Zhiwu, Huang, WANG, Naiyan |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6261 https://ink.library.smu.edu.sg/context/sis_research/article/7264/viewcontent/Direct_Differentiable_Augmentation_Search.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Efficient conditional GAN transfer with knowledge propagation across classes
by: Shahbazi. Mohamad,, et al.
Published: (2021) -
OPAQUE: Protecting Path Privacy in Directions Search
by: LEE, Ken C. K., et al.
Published: (2009) -
A unified dialogue user simulator for few-shot data augmentation
by: WAN, Dazhen, et al.
Published: (2022) -
Mobile visual search via hievarchical sparse coding
by: Yang, Xiyu, et al.
Published: (2014) -
PeerDA: Data augmentation via modeling peer relation for span identification tasks
by: XU, Weiwen, et al.
Published: (2023)