RepVGG: Making VGG-style ConvNets Great Again

• URL: http://arxiv.org/abs/2101.03697v3
• Date: Mon, 29 Mar 2021 13:02:36 GMT
• Title: RepVGG: Making VGG-style ConvNets Great Again
• Authors: Xiaohan Ding, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, Jian Sun
• Abstract summary: We present a simple but powerful architecture of convolutional neural network, which has a VGG-like inference-time body composed of nothing but a stack of 3x3 convolution and ReLU. RepVGG reaches over 80% top-1 accuracy, which is the first time for a plain model, to the best of our knowledge.
• Score: 116.0327370719692
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a simple but powerful architecture of convolutional neural network, which has a VGG-like inference-time body composed of nothing but a stack of 3x3 convolution and ReLU, while the training-time model has a multi-branch topology. Such decoupling of the training-time and inference-time architecture is realized by a structural re-parameterization technique so that the model is named RepVGG. On ImageNet, RepVGG reaches over 80% top-1 accuracy, which is the first time for a plain model, to the best of our knowledge. On NVIDIA 1080Ti GPU, RepVGG models run 83% faster than ResNet-50 or 101% faster than ResNet-101 with higher accuracy and show favorable accuracy-speed trade-off compared to the state-of-the-art models like EfficientNet and RegNet. The code and trained models are available at https://github.com/megvii-model/RepVGG.

Related papers

• DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation [8.240211805240023]
  We revisit the design of atrous convolutions in modern convolutional neural networks (CNNs) We propose DSNet, a Dual-Branch CNN architecture, which incorporates atrous convolutions in the shallow layers of the model architecture. Our models achieve a new state-of-the-art trade-off between accuracy and speed on ADE20K, Cityscapes and BDD datasets.
  arXiv  Detail & Related papers  (2024-06-06T02:51:57Z)
• ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders [104.05133094625137]
  We propose a fully convolutional masked autoencoder framework and a new Global Response Normalization layer. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets.
  arXiv  Detail & Related papers  (2023-01-02T18:59:31Z)
• Re-parameterizing Your Optimizers rather than Architectures [119.08740698936633]
  We propose a novel paradigm of incorporating model-specific prior knowledge into Structurals and using them to train generic (simple) models. As an implementation, we propose a novel methodology to add prior knowledge by modifying the gradients according to a set of model-specific hyper- parameters. For a simple model trained with a Repr, we focus on a VGG-style plain model and showcase that such a simple model trained with a Repr, which is referred to as Rep-VGG, performs on par with the recent well-designed models.
  arXiv  Detail & Related papers  (2022-05-30T16:55:59Z)
• RMNet: Equivalently Removing Residual Connection from Networks [15.32653042487324]
  We propose to remove the residual connection in a vanilla ResNet equivalently by a reserving and merging (RM) operation on ResBlock. As a plug-in method, RM Operation basically has three advantages: 1) its implementation makes it naturally friendly for high ratio network pruning, 2) it helps break the depth limitation of RepVGG, and 3) it leads to better accuracy-speed trade-off network (RMNet) compared to ResNet and RepVGG.
  arXiv  Detail & Related papers  (2021-11-01T04:07:45Z)
• EfficientNetV2: Smaller Models and Faster Training [91.77432224225221]
  This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. We use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. Our experiments show that EfficientNetV2 models train much faster than state-of-the-art models while being up to 6.8x smaller.
  arXiv  Detail & Related papers  (2021-04-01T07:08:36Z)
• FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining [65.39532971991778]
  We present an accuracy predictor that scores architecture and training recipes jointly, guiding both sample selection and ranking. We run fast evolutionary searches in just CPU minutes to generate architecture-recipe pairs for a variety of resource constraints. FBNetV3 makes up a family of state-of-the-art compact neural networks that outperform both automatically and manually-designed competitors.
  arXiv  Detail & Related papers  (2020-06-03T05:20:21Z)
• Improved Residual Networks for Image and Video Recognition [98.10703825716142]
  Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture. We show consistent improvements in accuracy and learning convergence over the baseline. Our proposed approach allows us to train extremely deep networks, while the baseline shows severe optimization issues.
  arXiv  Detail & Related papers  (2020-04-10T11:09:50Z)
• TResNet: High Performance GPU-Dedicated Architecture [6.654949459658242]
  Many deep learning models, developed in recent years, reach higher ImageNet accuracy than ResNet50, with fewer or comparable FLOPS count. In this work, we introduce a series of architecture modifications that aim to boost neural networks' accuracy, while retaining their GPU training and inference efficiency. We introduce a new family of GPU-dedicated models, called TResNet, which achieve better accuracy and efficiency than previous ConvNets.
  arXiv  Detail & Related papers  (2020-03-30T17:04:47Z)

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.