Few-Shot Guided Mix for DNN Repairing

Xuhong Ren, Bing Yu, Hua Qi, Felix Juefei-Xu, Zhuo Li, Wanli Xue, Lei Ma, Jianjun Zhao

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

抄録

Although deep neural networks (DNNs) achieve rather high performance in many cutting-edge applications (e.g., autonomous driving, medical diagnose), their trustworthiness on real-world scenarios still posts concerns, where some specific failure examples are often encountered during the real-world operational environment. With the limited failure examples collected during the practical operation, how to effectively leverage such failure cases to repair and enhance DNN so as to generalize to more potentially suspicious samples is challenging, but of great importance. In this paper, we formulate the failure-data-driven DNN repairing as a data augmentation problem, and design a novel augmentation-based repairing method, which to the best extent leverages limited failure cases. To realize the DNN repairing effects that generalize to specific failure examples, we originally propose few-shot guided mix (FSGMix) that augments training data with the guidance of failure examples. As a result, our method is able to achieve high generalization to the collected failure examples and other similar suspicious data. The preliminary evaluation on CIFAR-10 dataset demonstrates the potential of our proposed technique, which automatically learns to resolve the potential failure patterns in the DNN operational environment.

本文言語英語
ホスト出版物のタイトルProceedings - 2020 IEEE International Conference on Software Maintenance and Evolution, ICSME 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ717-721
ページ数5
ISBN(電子版)9781728156194
DOI
出版ステータス出版済み - 9 2020
イベント36th IEEE International Conference on Software Maintenance and Evolution, ICSME 2020 - Virtual, Adelaide, オーストラリア
継続期間: 9 27 202010 3 2020

出版物シリーズ

名前Proceedings - 2020 IEEE International Conference on Software Maintenance and Evolution, ICSME 2020

会議

会議36th IEEE International Conference on Software Maintenance and Evolution, ICSME 2020
Countryオーストラリア
CityVirtual, Adelaide
Period9/27/2010/3/20

All Science Journal Classification (ASJC) codes

  • Software
  • Safety, Risk, Reliability and Quality
  • Modelling and Simulation

フィンガープリント 「Few-Shot Guided Mix for DNN Repairing」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル