# A Multiple Classifier Approach for Concatenate-Designed Neural Networks

arXiv: https://arxiv.org/abs/2101.05457 · HTML: https://mlsanity.com/paper/2101.05457/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 65 references that are in the map.
- First posted on arXiv 14 Jan 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Wider or Deeper: Revisiting the ResNet Model for Visual Recognition](https://mlsanity.com/paper/1611.10080/) (2016)
- [DeepID3: Face Recognition with Very Deep Neural Networks](https://mlsanity.com/paper/1502.00873/) (2015)
- [Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery](https://mlsanity.com/paper/1711.09082/) (2017)
- [An All-In-One Convolutional Neural Network for Face Analysis](https://mlsanity.com/paper/1611.00851/) (2016)
- [Training Deeper Convolutional Networks with Deep Supervision](https://mlsanity.com/paper/1505.02496/) (2015)
- [Distance-based Confidence Score for Neural Network Classifiers](https://mlsanity.com/paper/1709.09844/) (2017)
- [Deep Neural Network for Real-Time Autonomous Indoor Navigation](https://mlsanity.com/paper/1511.04668/) (2015)
- [Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images](https://mlsanity.com/paper/2008.06258/) (2020)
- [Dynamic voting in multi-view learning for radiomics applications](https://mlsanity.com/paper/1806.07686/) (2018)
- [Sharing Residual Units Through Collective Tensor Factorization in Deep Neural Networks](https://mlsanity.com/paper/1703.02180/) (2017)
- [Identity Recognition in Intelligent Cars with Behavioral Data and LSTM-ResNet Classifier](https://mlsanity.com/paper/2003.00770/) (2020)

## Abstract (arXiv)

This article introduces a multiple classifier method to improve the performance of concatenate-designed neural networks, such as ResNet and DenseNet, with the purpose to alleviate the pressure on the final classifier. We give the design of the classifiers, which collects the features produced between the network sets, and present the constituent layers and the activation function for the classifiers, to calculate the classification score of each classifier. We use the L2 normalization method to obtain the classifier score instead of the Softmax normalization. We also determine the conditions that can enhance convergence. As a result, the proposed classifiers are able to improve the accuracy in the experimental cases significantly, and show that the method not only has better performance than the original models, but also produces faster convergence. Moreover, our classifiers are general and can be applied to all classification related concatenate-designed network models.