COMET: Coverage-guided Model Generation For Deep Learning Library Testing

no code implementations • 2 Aug 2022 • Meiziniu Li, Jialun Cao, Yongqiang Tian, Tsz On Li, Ming Wen, Shing-Chi Cheung

Techniques have been proposed to generate various DL models and apply them to test these libraries.

DeepFD: Automated Fault Diagnosis and Localization for Deep Learning Programs

1 code implementation • 4 May 2022 • Jialun Cao, Meiziniu Li, Xiao Chen, Ming Wen, Yongqiang Tian, Bo Wu, Shing-Chi Cheung

Besides, for fault localization, DeepFD also outperforms the existing works, correctly locating 42% faulty programs, which almost doubles the best result (23%) achieved by the existing works.

Fault localization

Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications

1 code implementation • 6 Dec 2021 • Yongqiang Tian, Wuqi Zhang, Ming Wen, Shing-Chi Cheung, Chengnian Sun, Shiqing Ma, Yu Jiang

To this end, we propose DFLARE, a novel, search-based, black-box testing technique to automatically find triggering inputs that result in deviated behaviors in image classification tasks.

Image Classification Model Compression

Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations

no code implementations • 6 Sep 2019 • Yongqiang Tian, Shiqing Ma, Ming Wen, Yepang Liu, Shing-Chi Cheung, Xiangyu Zhang

The corresponding rate for the object detection models is over 8. 5%.

General Classification Image Classification +4