# Patching Weak Convolutional Neural Network Models through Modularization and Composition

arXiv: https://arxiv.org/abs/2209.06116 · HTML: https://mlsanity.com/paper/2209.06116/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 50 references that are in the map.
- First posted on arXiv 11 Sep 2022.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [Hierarchical Representations for Efficient Architecture Search](https://mlsanity.com/paper/1711.00436/) (2017)
- [Genetic CNN](https://mlsanity.com/paper/1703.01513/) (2017)
- [Modular Networks: Learning to Decompose Neural Computation](https://mlsanity.com/paper/1811.05249/) (2018)
- [Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search](https://mlsanity.com/paper/1803.00370/) (2018)
- [Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules](https://mlsanity.com/paper/2110.07720/) (2021)
- [Neural Network Module Decomposition and Recomposition](https://mlsanity.com/paper/2112.13208/) (2021)
- [Improving Test Case Generation for REST APIs Through Hierarchical Clustering](https://mlsanity.com/paper/2109.06655/) (2021)

## Built on by (most cited first, 6 of 6)

- [Reusing Deep Neural Network Models through Model Re-engineering](https://mlsanity.com/paper/2304.00245/) (2023)
- [Modularizing while Training: A New Paradigm for Modularizing DNN Models](https://mlsanity.com/paper/2306.09376/) (2023)
- [DNN Modularization via Activation-Driven Training](https://mlsanity.com/paper/2411.01074/) (2024)
- [On Accelerating Deep Neural Network Mutation Analysis by Neuron and Mutant Clustering](https://mlsanity.com/paper/2501.12598/) (2025)
- [NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models](https://mlsanity.com/paper/2508.11348/) (2025)
- [Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models](https://mlsanity.com/paper/2610.05277/) (2026)

## Abstract (arXiv)

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.