Structural Pruning via Spatial-aware Information Redundancy for Semantic Segmentation

TL;DR

This paper introduces SIRFP, a novel spatial-aware filter pruning method for semantic segmentation that reduces redundancy by formulating pruning as a graph problem, leading to improved efficiency and performance.

Contribution

The paper proposes a spatial-aware redundancy metric and formulates pruning as a maximum edge weight clique problem, enhancing segmentation network pruning effectiveness.

Findings

SIRFP outperforms existing pruning methods on multiple datasets.

The proposed method achieves significant computational savings.

SIRFP maintains high segmentation accuracy after pruning.

Abstract

In recent years, semantic segmentation has flourished in various applications. However, the high computational cost remains a significant challenge that hinders its further adoption. The filter pruning method for structured network slimming offers a direct and effective solution for the reduction of segmentation networks. Nevertheless, we argue that most existing pruning methods, originally designed for image classification, overlook the fact that segmentation is a location-sensitive task, which consequently leads to their suboptimal performance when applied to segmentation networks. To address this issue, this paper proposes a novel approach, denoted as Spatial-aware Information Redundancy Filter Pruning~(SIRFP), which aims to reduce feature redundancy between channels. First, we formulate the pruning process as a maximum edge weight clique problem~(MEWCP) in graph theory, thereby minimizing the redundancy among the remaining features after pruning. Within this framework, we introduce a spatial-aware redundancy metric based on feature maps, thus endowing the pruning process with location sensitivity to better adapt to pruning segmentation networks. Additionally, based on the MEWCP, we propose a low computational complexity greedy strategy to solve this NP-hard problem, making it feasible and efficient for structured pruning. To validate the effectiveness of our method, we conducted extensive comparative experiments on various challenging datasets. The results demonstrate the superior performance of SIRFP for semantic segmentation tasks.