DeepRepair: Style-guided repairing for deep neural networks in the real-world operational environment
Deep neural networks (DNNs) are continuously expanding their application to various domains due to their high performance. Nevertheless, a well-trained DNN after deployment could oftentimes raise errors during practical use in the operational environment due to the mismatching between distributions...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7051 https://ink.library.smu.edu.sg/context/sis_research/article/8054/viewcontent/camera_ready.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-8054 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-80542022-04-07T09:08:09Z DeepRepair: Style-guided repairing for deep neural networks in the real-world operational environment YU, Bing QI, Hua QING, Guo JUEFEI-XU, Felix XIE, Xiaofei MA, Lei ZHAO, Jianjun Deep neural networks (DNNs) are continuously expanding their application to various domains due to their high performance. Nevertheless, a well-trained DNN after deployment could oftentimes raise errors during practical use in the operational environment due to the mismatching between distributions of the training dataset and the potential unknown noise factors in the operational environment, e.g., weather, blur, noise, etc. Hence, it poses a rather important problem for the DNNs' real-world applications: how to repair the deployed DNNs for correcting the failure samples under the deployed operational environment while not harming their capability of handling normal or clean data with limited failure samples we can collect. In this article, we propose a style-guided data augmentation for repairing DNN in the operational environment, which learns and introduces the unknown failure patterns within the failure samples into the training data via the style transfer. Moreover, we further propose the clustering-based failure data generation for much more effective style-guided data augmentation. We conduct a large-scale evaluation with 15 degradation factors that may happen in the real world and compare with four state-of-the-art data augmentation methods and two DNN repairing methods. Our technique successfully repairs three convolutional neural networks and two recurrent neural networks with averaging 62.88% and 39.02% accuracy enhancements on the 15 failure patterns, respectively, achieving higher repairing performance than state-of-the-art repairing methods on the most failure patterns with even better accuracy on clean datasets. 2021-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7051 info:doi/10.1109/TR.2021.3096332 https://ink.library.smu.edu.sg/context/sis_research/article/8054/viewcontent/camera_ready.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Training Maintenance engineering Software Data models Training data Neurons Games Data augmentation deep neural network (DNN) repairing deep neural network operational environment OS and Networks Software Engineering |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Training Maintenance engineering Software Data models Training data Neurons Games Data augmentation deep neural network (DNN) repairing deep neural network operational environment OS and Networks Software Engineering |
spellingShingle |
Training Maintenance engineering Software Data models Training data Neurons Games Data augmentation deep neural network (DNN) repairing deep neural network operational environment OS and Networks Software Engineering YU, Bing QI, Hua QING, Guo JUEFEI-XU, Felix XIE, Xiaofei MA, Lei ZHAO, Jianjun DeepRepair: Style-guided repairing for deep neural networks in the real-world operational environment |
description |
Deep neural networks (DNNs) are continuously expanding their application to various domains due to their high performance. Nevertheless, a well-trained DNN after deployment could oftentimes raise errors during practical use in the operational environment due to the mismatching between distributions of the training dataset and the potential unknown noise factors in the operational environment, e.g., weather, blur, noise, etc. Hence, it poses a rather important problem for the DNNs' real-world applications: how to repair the deployed DNNs for correcting the failure samples under the deployed operational environment while not harming their capability of handling normal or clean data with limited failure samples we can collect. In this article, we propose a style-guided data augmentation for repairing DNN in the operational environment, which learns and introduces the unknown failure patterns within the failure samples into the training data via the style transfer. Moreover, we further propose the clustering-based failure data generation for much more effective style-guided data augmentation. We conduct a large-scale evaluation with 15 degradation factors that may happen in the real world and compare with four state-of-the-art data augmentation methods and two DNN repairing methods. Our technique successfully repairs three convolutional neural networks and two recurrent neural networks with averaging 62.88% and 39.02% accuracy enhancements on the 15 failure patterns, respectively, achieving higher repairing performance than state-of-the-art repairing methods on the most failure patterns with even better accuracy on clean datasets. |
format |
text |
author |
YU, Bing QI, Hua QING, Guo JUEFEI-XU, Felix XIE, Xiaofei MA, Lei ZHAO, Jianjun |
author_facet |
YU, Bing QI, Hua QING, Guo JUEFEI-XU, Felix XIE, Xiaofei MA, Lei ZHAO, Jianjun |
author_sort |
YU, Bing |
title |
DeepRepair: Style-guided repairing for deep neural networks in the real-world operational environment |
title_short |
DeepRepair: Style-guided repairing for deep neural networks in the real-world operational environment |
title_full |
DeepRepair: Style-guided repairing for deep neural networks in the real-world operational environment |
title_fullStr |
DeepRepair: Style-guided repairing for deep neural networks in the real-world operational environment |
title_full_unstemmed |
DeepRepair: Style-guided repairing for deep neural networks in the real-world operational environment |
title_sort |
deeprepair: style-guided repairing for deep neural networks in the real-world operational environment |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2021 |
url |
https://ink.library.smu.edu.sg/sis_research/7051 https://ink.library.smu.edu.sg/context/sis_research/article/8054/viewcontent/camera_ready.pdf |
_version_ |
1770576195363012608 |