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

• URL: http://arxiv.org/abs/2602.14040v1
• Date: Sun, 15 Feb 2026 08:07:19 GMT
• Title: Explainability-Inspired Layer-Wise Pruning of Deep Neural Networks for Efficient Object Detection
• Authors: Abhinav Shukla, Nachiket Tapas,
• Abstract summary: We present an explainability-inspired, layer-wise pruning framework tailored for efficient object detection.<n>We conduct experiments across diverse object detection architectures, including ResNet-50, MobileNetV2, ShuffleNetV2, Faster R-CNN, RetinaNet, and YOLOv8.<n>Results show that the proposed attribution-inspired pruning consistently identifies different layers as least important compared to L1-norm-based methods.
• Score: 3.317338104573978
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Towards Extreme Pruning of LLMs with Plug-and-Play Mixed Sparsity [32.668409666483626]
  Existing pruning methods mainly focus on designing metrics to measure the importance of network components to guide pruning.<n>We propose an efficient method based on the trace of Fisher Information Matrix (FIM) to quantitatively measure and verify the different sensitivities across layers.<n>Based on this, we propose Mixed Sparsity Pruning (MSP) which uses a pruning-oriented evolutionary algorithm (EA) to determine the optimal sparsity levels for different layers.
  arXiv  Detail & Related papers  (2025-03-14T08:05:49Z)
• LeYOLO, New Embedded Architecture for Object Detection [0.0]
  We introduce two key contributions to object detection models using MSCOCO as a base validation set.<n>First, we propose LeNeck, a general-purpose detection framework that maintains inference speed comparable to SSDLite.<n>Second, we present LeYOLO, an efficient object detection model designed to enhance computational efficiency in YOLO-based architectures.
  arXiv  Detail & Related papers  (2024-06-20T12:08:24Z)
• Block Pruning for Enhanced Efficiency in Convolutional Neural Networks [7.110116320545541]
  This paper presents a novel approach to network pruning, targeting block pruning in deep neural networks for edge computing environments. Our method diverges from traditional techniques that utilize proxy metrics, instead employing a direct block removal strategy to assess the impact on classification accuracy.
  arXiv  Detail & Related papers  (2023-12-28T08:54:48Z)
• Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity [0.0]
  Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference latency. We propose a solution to induce semi-structured activation sparsity exploitable through minor runtime modifications. Our approach yields a speed improvement of $1.25 times$ with a minimal accuracy drop of $1.1%$ for the ResNet18 model on the ImageNet dataset.
  arXiv  Detail & Related papers  (2023-09-12T22:28:53Z)
• Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks [48.089501687522954]
  We propose a novel layer-adaptive weight-pruning approach for Deep Neural Networks (DNNs) Our approach takes into account the collective influence of all layers to design a layer-adaptive pruning scheme. Our experiments demonstrate the superiority of our approach over existing methods on the ImageNet and CIFAR-10 datasets.
  arXiv  Detail & Related papers  (2023-08-21T03:22:47Z)
• WeightMom: Learning Sparse Networks using Iterative Momentum-based pruning [0.0]
  We propose a weight based pruning approach in which the weights are pruned gradually based on their momentum of the previous iterations. We evaluate our approach on networks such as AlexNet, VGG16 and ResNet50 with image classification datasets such as CIFAR-10 and CIFAR-100.
  arXiv  Detail & Related papers  (2022-08-11T07:13:59Z)
• CondenseNet V2: Sparse Feature Reactivation for Deep Networks [87.38447745642479]
  Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency. We propose an alternative approach named sparse feature reactivation (SFR), aiming at actively increasing the utility of features for reusing. Our experiments show that the proposed models achieve promising performance on image classification (ImageNet and CIFAR) and object detection (MS COCO) in terms of both theoretical efficiency and practical speed.
  arXiv  Detail & Related papers  (2021-04-09T14:12:43Z)
• BiPointNet: Binary Neural Network for Point Clouds [73.07852523426224]
  BiPointNet is the first model binarization approach for efficient deep learning on point clouds. We show that BiPointNet gives an impressive 14.7x speedup and 18.9x storage saving on real-world resource-constrained devices.
  arXiv  Detail & Related papers  (2020-10-12T07:54:51Z)
• Revisiting Initialization of Neural Networks [72.24615341588846]
  We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix. Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
  arXiv  Detail & Related papers  (2020-04-20T18:12:56Z)
• Resolution Adaptive Networks for Efficient Inference [53.04907454606711]
  We propose a novel Resolution Adaptive Network (RANet), which is inspired by the intuition that low-resolution representations are sufficient for classifying "easy" inputs. In RANet, the input images are first routed to a lightweight sub-network that efficiently extracts low-resolution representations. High-resolution paths in the network maintain the capability to recognize the "hard" samples.
  arXiv  Detail & Related papers  (2020-03-16T16:54:36Z)
• ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions [76.05981545084738]
  We propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost. We first construct a baseline network by modifying and binarizing a compact real-valued network with parameter-free shortcuts. We show that the proposed ReActNet outperforms all the state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2020-03-07T02:12:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.