- Title
- Patching Weak Convolutional Neural Network Models through Modularization and Composition
- Creator
- Qi, Binhang; Sun, Hailong; Gao, Xiang; Zhang, Hongyu
- Relation
- ASE '22: 37th IEEE/ACM International Conference on Automated Software Engineering. Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering (Michigan, USA 10-14 October 2022) p. 1-12
- Relation
- ARC.DP200102940 http://purl.org/au-research/grants/arc/DP200102940
- Publisher Link
- http://dx.doi.org/10.1145/3551349.3561153
- Publisher
- Association for Computing Machinery
- Resource Type
- conference paper
- Date
- 2022
- Description
- Despite great success in many applications, deep neural networks are not always robust in practice. For instance, a convolutional neuron network (CNN) model for classification tasks often performs unsatisfactorily in classifying some particular classes of objects. In this work, we are concerned with patching the weak part of a CNN model instead of improving it through the costly retraining of the entire model. Inspired by the fundamental concepts of modularization and composition in software engineering, we propose a compressed modularization approach, CNNSplitter, which decomposes a strong CNN model for N-class classification into N smaller CNN modules. Each module is a sub-model containing a part of the convolution kernels of the strong model. To patch a weak CNN model that performs unsatisfactorily on a target class (TC), we compose the weak CNN model with the corresponding module obtained from a strong CNN model. The ability of the weak CNN model to recognize the TC can thus be improved through patching. Moreover, the ability to recognize non-TCs is also improved, as the samples misclassified as TC could be classified as non-TCs correctly. Experimental results with two representative CNNs on three widely-used datasets show that the averaged improvement on the TC in terms of precision and recall are 12.54% and 2.14%, respectively. Moreover, patching improves the accuracy of non-TCs by 1.18%. The results demonstrate that CNNSplitter can patch a weak CNN model through modularization and composition, thus providing a new solution for developing robust CNN models.
- Subject
- modularisation; DNN; CNN; patching
- Identifier
- http://hdl.handle.net/1959.13/1486620
- Identifier
- uon:51907
- Identifier
- ISBN:9781450396240
- Language
- eng
- Reviewed
- Hits: 654
- Visitors: 654
- Downloads: 0
| Thumbnail | File | Description | Size | Format |
|---|