Omni-Dimensional Dynamic Convolution

• URL: http://arxiv.org/abs/2209.07947v1
• Date: Fri, 16 Sep 2022 14:05:38 GMT
• Title: Omni-Dimensional Dynamic Convolution
• Authors: Chao Li, Aojun Zhou, Anbang Yao
• Abstract summary: Learning a single static convolutional kernel in each convolutional layer is the common training paradigm of modern Convolutional Neural Networks (CNNs) Recent research in dynamic convolution shows that learning a linear combination of $n$ convolutional kernels weighted with their input-dependent attentions can significantly improve the accuracy of light-weight CNNs. We present Omni-dimensional Dynamic Convolution (ODConv), a more generalized yet elegant dynamic convolution design.
• Score: 25.78940854339179
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning a single static convolutional kernel in each convolutional layer is the common training paradigm of modern Convolutional Neural Networks (CNNs). Instead, recent research in dynamic convolution shows that learning a linear combination of $n$ convolutional kernels weighted with their input-dependent attentions can significantly improve the accuracy of light-weight CNNs, while maintaining efficient inference. However, we observe that existing works endow convolutional kernels with the dynamic property through one dimension (regarding the convolutional kernel number) of the kernel space, but the other three dimensions (regarding the spatial size, the input channel number and the output channel number for each convolutional kernel) are overlooked. Inspired by this, we present Omni-dimensional Dynamic Convolution (ODConv), a more generalized yet elegant dynamic convolution design, to advance this line of research. ODConv leverages a novel multi-dimensional attention mechanism with a parallel strategy to learn complementary attentions for convolutional kernels along all four dimensions of the kernel space at any convolutional layer. As a drop-in replacement of regular convolutions, ODConv can be plugged into many CNN architectures. Extensive experiments on the ImageNet and MS-COCO datasets show that ODConv brings solid accuracy boosts for various prevailing CNN backbones including both light-weight and large ones, e.g., 3.77%~5.71%|1.86%~3.72% absolute top-1 improvements to MobivleNetV2|ResNet family on the ImageNet dataset. Intriguingly, thanks to its improved feature learning ability, ODConv with even one single kernel can compete with or outperform existing dynamic convolution counterparts with multiple kernels, substantially reducing extra parameters. Furthermore, ODConv is also superior to other attention modules for modulating the output features or the convolutional weights.

Related papers

• KernelWarehouse: Rethinking the Design of Dynamic Convolution [16.101179962553385]
  KernelWarehouse redefines the basic concepts of Kernels", assembling kernels" and attention function" We testify the effectiveness of KernelWarehouse on ImageNet and MS-COCO datasets using various ConvNet architectures.
  arXiv  Detail & Related papers  (2024-06-12T05:16:26Z)
• ParCNetV2: Oversized Kernel with Enhanced Attention [60.141606180434195]
  We introduce a convolutional neural network architecture named ParCNetV2. It extends position-aware circular convolution (ParCNet) with oversized convolutions and strengthens attention through bifurcate gate units. Our method outperforms other pure convolutional neural networks as well as neural networks hybridizing CNNs and transformers.
  arXiv  Detail & Related papers  (2022-11-14T07:22:55Z)
• DualConv: Dual Convolutional Kernels for Lightweight Deep Neural Networks [31.520543731423455]
  We propose dual convolutional kernels (DualConv) for constructing lightweight deep neural networks. We extensively test DualConv for classification since these network architectures form the backbones for many other tasks. Experimental results show that, combined with our structural innovations, DualConv significantly reduces the computational cost and number of parameters of deep neural networks.
  arXiv  Detail & Related papers  (2022-02-15T14:47:13Z)
• Hyper-Convolutions via Implicit Kernels for Medical Imaging [18.98078260974008]
  We present the textithyper-convolution, a novel building block that implicitly encodes the convolutional kernel using spatial coordinates. We demonstrate in our experiments that replacing regular convolutions with hyper-convolutions can improve performance with less parameters, and increase robustness against noise.
  arXiv  Detail & Related papers  (2022-02-06T03:56:19Z)
• PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds [33.41204351513122]
  PAConv is a generic convolution operation for 3D point cloud processing. The kernel is built in a data-driven manner, endowing PAConv with more flexibility than 2D convolutions. Even built on simple networks, our method still approaches or even surpasses the state-of-the-art models.
  arXiv  Detail & Related papers  (2021-03-26T17:52:38Z)
• Revisiting Dynamic Convolution via Matrix Decomposition [81.89967403872147]
  We propose dynamic channel fusion to replace dynamic attention over channel groups. Our method is easier to train and requires significantly fewer parameters without sacrificing accuracy.
  arXiv  Detail & Related papers  (2021-03-15T23:03:18Z)
• PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer [76.44375136492827]
  Convolutional Neural Networks (CNNs) are often scale-sensitive. We bridge this regret by exploiting multi-scale features in a finer granularity. The proposed convolution operation, named Poly-Scale Convolution (PSConv), mixes up a spectrum of dilation rates.
  arXiv  Detail & Related papers  (2020-07-13T05:14:11Z)
• DO-Conv: Depthwise Over-parameterized Convolutional Layer [66.46704754669169]
  We propose to augment a convolutional layer with an additional depthwise convolution, where each input channel is convolved with a different 2D kernel. We show with extensive experiments that the mere replacement of conventional convolutional layers with DO-Conv layers boosts the performance of CNNs.
  arXiv  Detail & Related papers  (2020-06-22T06:57:10Z)
• 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)
• XSepConv: Extremely Separated Convolution [60.90871656244126]
  We propose a novel extremely separated convolutional block (XSepConv) It fuses spatially separable convolutions into depthwise convolution to reduce both the computational cost and parameter size of large kernels. XSepConv is designed to be an efficient alternative to vanilla depthwise convolution with large kernel sizes.
  arXiv  Detail & Related papers  (2020-02-27T11:46:17Z)

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.