Neural Network Pruning for Real-time Polyp Segmentation

TL;DR

This paper demonstrates that neural network pruning using TaylorFO importance scores can significantly reduce model size and computational cost in real-time polyp segmentation without sacrificing accuracy.

Contribution

The study introduces a pruning method based on TaylorFO importance scores specifically applied to polyp segmentation models, maintaining performance while reducing complexity.

Findings

Significant reduction in parameters and FLOPs achieved.

Performance retained despite pruning.

Effective importance scoring with gradient-normalized backpropagation.

Abstract

Computer-assisted treatment has emerged as a viable application of medical imaging, owing to the efficacy of deep learning models. Real-time inference speed remains a key requirement for such applications to help medical personnel. Even though there generally exists a trade-off between performance and model size, impressive efforts have been made to retain near-original performance by compromising model size. Neural network pruning has emerged as an exciting area that aims to eliminate redundant parameters to make the inference faster. In this study, we show an application of neural network pruning in polyp segmentation. We compute the importance score of convolutional filters and remove the filters having the least scores, which to some value of pruning does not degrade the performance. For computing the importance score, we use the Taylor First Order (TaylorFO) approximation of the change in network output for the removal of certain filters. Specifically, we employ a gradient-normalized backpropagation for the computation of the importance score. Through experiments in the polyp datasets, we validate that our approach can significantly reduce the parameter count and FLOPs retaining similar performance.