# HSD-CNN: Hierarchically self decomposing CNN architecture using class specific filter sensitivity analysis

arXiv: https://arxiv.org/abs/1811.04406 · HTML: https://mlsanity.com/paper/1811.04406/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2018.

## Built on by (most cited first, 2 of 2)

- [Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules](https://mlsanity.com/paper/2110.07720/) (2021)
- [Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement](https://mlsanity.com/paper/2212.05970/) (2022)

## Abstract (arXiv)

Conventional Convolutional neural networks (CNN) are trained on large domain datasets and are hence typically over-represented and inefficient in limited class applications. An efficient way to convert such large many-class pre-trained networks into small few-class networks is through a hierarchical decomposition of its feature maps. To alleviate this issue, we propose an automated framework for such decomposition in Hierarchically Self Decomposing CNN (HSD-CNN), in four steps. HSD-CNN is derived automatically using a class-specific filter sensitivity analysis that quantifies the impact of specific features on a class prediction. The decomposed hierarchical network can be utilized and deployed directly to obtain sub-networks for a subset of classes, and it is shown to perform better without the requirement of retraining these sub-networks. Experimental results show that HSD-CNN generally does not degrade accuracy if the full set of classes are used. Interestingly, when operating on known subsets of classes, HSD-CNN has an improvement in accuracy with a much smaller model size, requiring much fewer operations. HSD-CNN flow is verified on the CIFAR10, CIFAR100 and CALTECH101 data sets. We report accuracies up to 85.6% ( 94.75% ) on scenarios with 13 ( 4 ) classes of CIFAR100, using a pre-trained VGG-16 network on the full data set. In this case, the proposed HSD-CNN requires 3.97 × fewer parameters and has 71.22% savings in operations, in comparison to baseline VGG-16 containing features for all 100 classes.