Logo image
Efficient Distortion-Minimized Layerwise Pruning
Journal article   Peer reviewed

Efficient Distortion-Minimized Layerwise Pruning

Kaixin Xu, Zhe Wang, Runtao Huang, Xue Geng, Jie Lin, Xulei Yang, Min Wu, Xiaoli Li and Weisi Lin
IEEE transactions on pattern analysis and machine intelligence, Vol.47(10), pp.9298-9315
01/10/2025
PMID: 40622829

Abstract

Accuracy Deep learning Distortion Dynamic programming Heuristic algorithms model compression Object detection Optimization post-training pruning rate-distortion theory Resource management Solid modeling Three-dimensional displays Training
In this paper, we propose a post-training pruning framework that jointly optimizes layerwise pruning to minimize model output distortion. Through theoretical and empirical analysis, we discover an important additivity property of output distortion from pruning weights/channels in DNNs. Leveraging this property, we reformulate pruning optimization as a combinatorial problem and solve it with dynamic programming, achieving linear time complexity and making the algorithm very fast on CPUs. Furthermore, we optimize additivity-derived distortions using Hessian-based Taylor approximation to enhance pruning efficiency, accompanied by fine-grained complexity reduction techniques. Our method is evaluated on various DNN architectures, including CNNs, ViTs, and object detectors, and on vision tasks such as image classification on CIFAR-10 and ImageNet, and 3D object detection and various datasets. We achieve SoTA with significant FLOPs reductions without accuracy loss. Specifically, on CIFAR-10, we achieve up to <inline-formula><tex-math notation="LaTeX">27.9\times</tex-math> <mml:math><mml:mrow><mml:mn>27</mml:mn><mml:mo>.</mml:mo><mml:mn>9</mml:mn><mml:mo>×</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="xu-ieq1-3586418.gif"/> </inline-formula>, <inline-formula><tex-math notation="LaTeX">29.2\times</tex-math> <mml:math><mml:mrow><mml:mn>29</mml:mn><mml:mo>.</mml:mo><mml:mn>2</mml:mn><mml:mo>×</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="xu-ieq2-3586418.gif"/> </inline-formula>, and <inline-formula><tex-math notation="LaTeX">14.9\times</tex-math> <mml:math><mml:mrow><mml:mn>14</mml:mn><mml:mo>.</mml:mo><mml:mn>9</mml:mn><mml:mo>×</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="xu-ieq3-3586418.gif"/> </inline-formula> FLOPs reductions on ResNet-32, VGG-16, and DenseNet-121, respectively. On ImageNet, we observe no accuracy loss with <inline-formula><tex-math notation="LaTeX">1.69\times</tex-math> <mml:math><mml:mrow><mml:mn>1</mml:mn><mml:mo>.</mml:mo><mml:mn>69</mml:mn><mml:mo>×</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="xu-ieq4-3586418.gif"/> </inline-formula> and <inline-formula><tex-math notation="LaTeX">2\times</tex-math> <mml:math><mml:mrow><mml:mn>2</mml:mn><mml:mo>×</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="xu-ieq5-3586418.gif"/> </inline-formula> FLOPs reductions on ResNet-50 and DeiT-Base, respectively. For 3D object detection, we achieve <inline-formula><tex-math notation="LaTeX">\mathbf {3.89}\times, \mathbf {3.72}\times</tex-math> <mml:math><mml:mrow><mml:mn mathvariant="bold">3</mml:mn><mml:mo>.</mml:mo><mml:mn mathvariant="bold">89</mml:mn><mml:mo>×</mml:mo><mml:mo>,</mml:mo><mml:mn mathvariant="bold">3</mml:mn><mml:mo>.</mml:mo><mml:mn mathvariant="bold">72</mml:mn><mml:mo>×</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="xu-ieq6-3586418.gif"/> </inline-formula> FLOPs reductions on CenterPoint and PVRCNN models. These results demonstrate the effectiveness and practicality of our approach for improving model performance through layer-adaptive weight pruning.

Metrics

1 Record Views

Details

Logo image