ResNet Structure Simplification with the Convolutional Kernel Redundancy Measure

• URL: http://arxiv.org/abs/2212.00272v1
• Date: Thu, 1 Dec 2022 04:29:28 GMT
• Title: ResNet Structure Simplification with the Convolutional Kernel Redundancy Measure
• Authors: Hongzhi Zhu, Robert Rohling, Septimiu Salcudean
• Abstract summary: We propose a quantifiable evaluation method, the convolutional kernel redundancy measure, for guiding the network structure simplification. Our method can maintain the performance of the network and reduce the number of parameters from over $23$ million to approximately $128$ thousand.
• Score: 3.8637285238278434
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deep learning, especially convolutional neural networks, has triggered accelerated advancements in computer vision, bringing changes into our daily practice. Furthermore, the standardized deep learning modules (also known as backbone networks), i.e., ResNet and EfficientNet, have enabled efficient and rapid development of new computer vision solutions. Yet, deep learning methods still suffer from several drawbacks. One of the most concerning problems is the high memory and computational cost, such that dedicated computing units, typically GPUs, have to be used for training and development. Therefore, in this paper, we propose a quantifiable evaluation method, the convolutional kernel redundancy measure, which is based on perceived image differences, for guiding the network structure simplification. When applying our method to the chest X-ray image classification problem with ResNet, our method can maintain the performance of the network and reduce the number of parameters from over $23$ million to approximately $128$ thousand (reducing $99.46\%$ of the parameters).

Related papers

• Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [72.26822499434446]
  Auto-Train-Once (ATO) is an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures.
  arXiv  Detail & Related papers  (2024-03-21T02:33:37Z)
• 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)
• A Generalization of Continuous Relaxation in Structured Pruning [0.3277163122167434]
  Trends indicate that deeper and larger neural networks with an increasing number of parameters achieve higher accuracy than smaller neural networks. We generalize structured pruning with algorithms for network augmentation, pruning, sub-network collapse and removal. The resulting CNN executes efficiently on GPU hardware without computationally expensive sparse matrix operations.
  arXiv  Detail & Related papers  (2023-08-28T14:19:13Z)
• Solving Large-scale Spatial Problems with Convolutional Neural Networks [88.31876586547848]
  We employ transfer learning to improve training efficiency for large-scale spatial problems. We propose that a convolutional neural network (CNN) can be trained on small windows of signals, but evaluated on arbitrarily large signals with little to no performance degradation.
  arXiv  Detail & Related papers  (2023-06-14T01:24:42Z)
• A Proper Orthogonal Decomposition approach for parameters reduction of Single Shot Detector networks [0.0]
  We propose a dimensionality reduction framework based on Proper Orthogonal Decomposition, a classical model order reduction technique. We have applied such framework to SSD300 architecture using PASCAL VOC dataset, demonstrating a reduction of the network dimension and a remarkable speedup in the fine-tuning of the network in a transfer learning context.
  arXiv  Detail & Related papers  (2022-07-27T14:43:14Z)
• Leveraging Structured Pruning of Convolutional Neural Networks [2.2320512724449233]
  We propose a method that is able to take any structured pruning mask and generate a network that does not encounter any of these problems. We show results of gains, in energy consumption and inference time on embedded hardware, of pruned convolutional neural networks.
  arXiv  Detail & Related papers  (2022-06-13T15:29:12Z)
• Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers [83.74380713308605]
  We develop a new type of transformation that is fully compatible with a variant of ReLUs -- Leaky ReLUs. We show in experiments that our method, which introduces negligible extra computational cost, validation accuracies with deep vanilla networks that are competitive with ResNets.
  arXiv  Detail & Related papers  (2022-03-15T17:49:08Z)
• Instant Neural Graphics Primitives with a Multiresolution Hash Encoding [67.33850633281803]
  We present a versatile new input encoding that permits the use of a smaller network without sacrificing quality. A small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through a gradient descent. We achieve a combined speed of several orders of magnitude, enabling training of high-quality neural graphics primitives in a matter of seconds.
  arXiv  Detail & Related papers  (2022-01-16T07:22:47Z)
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
  This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain. In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden. Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
  arXiv  Detail & Related papers  (2021-03-15T12:54:26Z)
• NAS-DIP: Learning Deep Image Prior with Neural Architecture Search [65.79109790446257]
  Recent work has shown that the structure of deep convolutional neural networks can be used as a structured image prior. We propose to search for neural architectures that capture stronger image priors. We search for an improved network by leveraging an existing neural architecture search algorithm.
  arXiv  Detail & Related papers  (2020-08-26T17:59:36Z)
• Knapsack Pruning with Inner Distillation [11.04321604965426]
  We propose a novel pruning method that optimize the final accuracy of the pruned network. We prune the network channels while maintaining the high-level structure of the network. Our method leads to state-of-the-art pruning results on ImageNet, CIFAR-10 and CIFAR-100 using ResNet backbones.
  arXiv  Detail & Related papers  (2020-02-19T16:04:48Z)

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.