Diffchaser: Detecting disagreements for deep neural networks

Xiaofei Xie, Lei Ma, Haijun Wang, Yuekang Li, Yang Liu, Xiaohong Li

研究成果: 著書/レポートタイプへの貢献会議での発言

11 引用 (Scopus)

抜粋

The platform migration and customization have become an indispensable process of deep neural network (DNN) development lifecycle. A high-precision but complex DNN trained in the cloud on massive data and powerful GPUS often goes through an optimization phase (e.g., quantization, compression) before deployment to a target device (e.g., mobile device). A test set that effectively uncovers the disagreements of a DNN and its optimized variant provides certain feedback to debug and further enhance the optimization procedure. However, the minor inconsistency between a DNN and its optimized version is often hard to detect and easily bypasses the original test set. This paper proposes DiffChaser, an automated black-box testing framework to detect untargeted/targeted disagreements between version variants of a DNN. We demonstrate 1) its effectiveness by comparing with the state-of-the-art techniques, and 2) its usefulness in real-world DNN product deployment involved with quantization and optimization.

元の言語英語
ホスト出版物のタイトルProceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
編集者Sarit Kraus
出版者International Joint Conferences on Artificial Intelligence
ページ5772-5778
ページ数7
ISBN(電子版)9780999241141
DOI
出版物ステータス出版済み - 1 1 2019
イベント28th International Joint Conference on Artificial Intelligence, IJCAI 2019 - Macao, 中国
継続期間: 8 10 20198 16 2019

出版物シリーズ

名前IJCAI International Joint Conference on Artificial Intelligence
2019-August
ISSN(印刷物)1045-0823

会議

会議28th International Joint Conference on Artificial Intelligence, IJCAI 2019
中国
Macao
期間8/10/198/16/19

    フィンガープリント

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

これを引用

Xie, X., Ma, L., Wang, H., Li, Y., Liu, Y., & Li, X. (2019). Diffchaser: Detecting disagreements for deep neural networks. : S. Kraus (版), Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019 (pp. 5772-5778). (IJCAI International Joint Conference on Artificial Intelligence; 巻数 2019-August). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2019/800