Dynamic Group Convolution for Accelerating Convolutional Neural Networks

• URL: http://arxiv.org/abs/2007.04242v2
• Date: Fri, 10 Jul 2020 17:24:31 GMT
• Title: Dynamic Group Convolution for Accelerating Convolutional Neural Networks
• Authors: Zhuo Su, Linpu Fang, Wenxiong Kang, Dewen Hu, Matti Pietik\"ainen, Li Liu
• Abstract summary: We propose dynamic group convolution (DGC) that adaptively selects which part of input channels to be connected within each group. Multiple groups can adaptively capture abundant and complementary visual/semantic features for each input image. The DGC preserves the original network structure and has similar computational efficiency as the conventional group convolution simultaneously.
• Score: 23.644124360336754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Replacing normal convolutions with group convolutions can significantly increase the computational efficiency of modern deep convolutional networks, which has been widely adopted in compact network architecture designs. However, existing group convolutions undermine the original network structures by cutting off some connections permanently resulting in significant accuracy degradation. In this paper, we propose dynamic group convolution (DGC) that adaptively selects which part of input channels to be connected within each group for individual samples on the fly. Specifically, we equip each group with a small feature selector to automatically select the most important input channels conditioned on the input images. Multiple groups can adaptively capture abundant and complementary visual/semantic features for each input image. The DGC preserves the original network structure and has similar computational efficiency as the conventional group convolution simultaneously. Extensive experiments on multiple image classification benchmarks including CIFAR-10, CIFAR-100 and ImageNet demonstrate its superiority over the existing group convolution techniques and dynamic execution methods. The code is available at https://github.com/zhuogege1943/dgc.

Related papers

• PreCM: The Padding-based Rotation Equivariant Convolution Mode for Semantic Segmentation [10.74841255987162]
  In this paper, we numerically construct the padding-based rotation equivariant convolution mode (PreCM) PreCM can be used not only for multi-scale images and convolution kernels, but also as a replacement component to replace multiple convolutions. Experiments show that PreCM-based networks can achieve better segmentation performance than the original and data augmentation-based networks.
  arXiv  Detail & Related papers  (2024-11-03T16:26:55Z)
• Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution [15.421294642126073]
  This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) It explores the broad "middle spectrum" area between channel pruning and conventional grouped convolution. MSGC benefits from the learnability, the core of channel pruning, for constructing its group topology, leading to better channel division.
  arXiv  Detail & Related papers  (2023-04-13T07:31:41Z)
• Dual Complementary Dynamic Convolution for Image Recognition [13.864357201410648]
  We propose a novel two-branch dual complementary dynamic convolution (DCDC) operator for convolutional neural networks (CNNs) The DCDC operator overcomes the limitations of vanilla convolution and most existing dynamic convolutions who capture only spatial-adaptive features. Experiments show that the DCDC operator based ResNets (DCDC-ResNets) significantly outperform vanilla ResNets and most state-of-the-art dynamic convolutional networks on image classification.
  arXiv  Detail & Related papers  (2022-11-11T12:32:12Z)
• Pushing the Efficiency Limit Using Structured Sparse Convolutions [82.31130122200578]
  We propose Structured Sparse Convolution (SSC), which leverages the inherent structure in images to reduce the parameters in the convolutional filter. We show that SSC is a generalization of commonly used layers (depthwise, groupwise and pointwise convolution) in efficient architectures'' Architectures based on SSC achieve state-of-the-art performance compared to baselines on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet classification benchmarks.
  arXiv  Detail & Related papers  (2022-10-23T18:37:22Z)
• Optimising for Interpretability: Convolutional Dynamic Alignment Networks [108.83345790813445]
  We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA Nets) Their core building blocks are Dynamic Alignment Units (DAUs), which are optimised to transform their inputs with dynamically computed weight vectors that align with task-relevant patterns. CoDA Nets model the classification prediction through a series of input-dependent linear transformations, allowing for linear decomposition of the output into individual input contributions.
  arXiv  Detail & Related papers  (2021-09-27T12:39:46Z)
• X-volution: On the unification of convolution and self-attention [52.80459687846842]
  We propose a multi-branch elementary module composed of both convolution and self-attention operation. The proposed X-volution achieves highly competitive visual understanding improvements.
  arXiv  Detail & Related papers  (2021-06-04T04:32:02Z)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• Self-grouping Convolutional Neural Networks [30.732298624941738]
  We propose a novel method of designing self-grouping convolutional neural networks, called SG-CNN. For each filter, we first evaluate the importance value of their input channels to identify the importance vectors. Using the resulting emphdata-dependent centroids, we prune the less important connections, which implicitly minimizes the accuracy loss of the pruning.
  arXiv  Detail & Related papers  (2020-09-29T06:24:32Z)
• Binarizing MobileNet via Evolution-based Searching [66.94247681870125]
  We propose a use of evolutionary search to facilitate the construction and training scheme when binarizing MobileNet. Inspired by one-shot architecture search frameworks, we manipulate the idea of group convolution to design efficient 1-Bit Convolutional Neural Networks (CNNs) Our objective is to come up with a tiny yet efficient binary neural architecture by exploring the best candidates of the group convolution.
  arXiv  Detail & Related papers  (2020-05-13T13:25:51Z)
• Dynamic Region-Aware Convolution [85.20099799084026]
  We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions. On ImageNet classification, DRConv-based ShuffleNetV2-0.5x achieves state-of-the-art performance of 67.1% at 46M multiply-adds level with 6.3% relative improvement.
  arXiv  Detail & Related papers  (2020-03-27T05:49:57Z)

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.