# Explainability-Inspired Layer-Wise Pruning of Deep Neural Networks for Efficient Object Detection

arXiv: https://arxiv.org/abs/2602.14040 · HTML: https://mlsanity.com/paper/2602.14040/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 15 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [NISP: Pruning Networks using Neuron Importance Score Propagation](https://mlsanity.com/paper/1711.05908/) (2017)
- [Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning](https://mlsanity.com/paper/1912.08881/) (2019)
- [Less is More: The Influence of Pruning on the Explainability of CNNs](https://mlsanity.com/paper/2302.08878/) (2023)
- [When Does Pruning Benefit Vision Representations?](https://mlsanity.com/paper/2507.01722/) (2025)
- [Compressing Deep Neural Networks Using Explainable AI](https://mlsanity.com/paper/2507.05286/) (2025)
- [Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation](https://mlsanity.com/paper/2404.14271/) (2024)

## Abstract (arXiv)

Deep neural networks (DNNs) have achieved remarkable success in object detection tasks, but their increasing complexity poses significant challenges for deployment on resource-constrained platforms. While model compression techniques such as pruning have emerged as essential tools, traditional magnitude-based pruning methods do not necessarily align with the true functional contribution of network components to task-specific performance. In this work, we present an explainability-inspired, layer-wise pruning framework tailored for efficient object detection. Our approach leverages a SHAP-inspired gradient--activation attribution to estimate layer importance, providing a data-driven proxy for functional contribution rather than relying solely on static weight magnitudes. We conduct comprehensive experiments across diverse object detection architectures, including ResNet-50, MobileNetV2, ShuffleNetV2, Faster R-CNN, RetinaNet, and YOLOv8, evaluating performance on the Microsoft COCO 2017 validation set. The results show that the proposed attribution-inspired pruning consistently identifies different layers as least important compared to L1-norm-based methods, leading to improved accuracy--efficiency trade-offs. Notably, for ShuffleNetV2, our method yields a 10% empirical increase in inference speed, whereas L1-pruning degrades performance by 13.7%. For RetinaNet, the proposed approach preserves the baseline mAP (0.151) with negligible impact on inference speed, while L1-pruning incurs a 1.3% mAP drop for a 6.2% speed increase. These findings highlight the importance of data-driven layer importance assessment and demonstrate that explainability-inspired compression offers a principled direction for deploying deep neural networks on edge and resource-constrained platforms while preserving both performance and interpretability.