EfficientNetV2: Smaller Models and Faster Training

• URL: http://arxiv.org/abs/2104.00298v1
• Date: Thu, 1 Apr 2021 07:08:36 GMT
• Title: EfficientNetV2: Smaller Models and Faster Training
• Authors: Mingxing Tan, Quoc V. Le
• Abstract summary: 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.
• Score: 91.77432224225221
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop this family of models, we use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. The models were searched from the search space enriched with new ops such as Fused-MBConv. Our experiments show that EfficientNetV2 models train much faster than state-of-the-art models while being up to 6.8x smaller. Our training can be further sped up by progressively increasing the image size during training, but it often causes a drop in accuracy. To compensate for this accuracy drop, we propose to adaptively adjust regularization (e.g., dropout and data augmentation) as well, such that we can achieve both fast training and good accuracy. With progressive learning, our EfficientNetV2 significantly outperforms previous models on ImageNet and CIFAR/Cars/Flowers datasets. By pretraining on the same ImageNet21k, our EfficientNetV2 achieves 87.3% top-1 accuracy on ImageNet ILSVRC2012, outperforming the recent ViT by 2.0% accuracy while training 5x-11x faster using the same computing resources. Code will be available at https://github.com/google/automl/efficientnetv2.

Related papers

• Achieving Pareto Optimality using Efficient Parameter Reduction for DNNs in Resource-Constrained Edge Environment [1.9055921262476347]
  This paper proposes an optimization of an existing Deep Neural Network (DNN) that improves its hardware utilization and facilitates on-device training for resource-constrained edge environments. We implement efficient parameter reduction strategies on Xception that shrink the model size without sacrificing accuracy, thus decreasing memory utilization during training.
  arXiv  Detail & Related papers  (2024-03-14T19:40:58Z)
• Effective pruning of web-scale datasets based on complexity of concept clusters [48.125618324485195]
  We present a method for pruning large-scale multimodal datasets for training CLIP-style models on ImageNet. We find that training on a smaller set of high-quality data can lead to higher performance with significantly lower training costs. We achieve a new state-of-the-art Imagehttps://info.arxiv.org/help/prep#commentsNet zero-shot accuracy and a competitive average zero-shot accuracy on 38 evaluation tasks.
  arXiv  Detail & Related papers  (2024-01-09T14:32:24Z)
• A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization [54.113083217869516]
  In this work, we first explore the computational redundancy part of the network. We then prune the redundancy blocks of the model and maintain the network performance. Thirdly, we propose a global-regional interactive (GRI) attention to speed up the computationally intensive attention part.
  arXiv  Detail & Related papers  (2023-12-24T15:37:47Z)
• Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement [68.44100784364987]
  We propose a strategy to improve a dataset once such that the accuracy of any model architecture trained on the reinforced dataset is improved at no additional training cost for users. We create a reinforced version of the ImageNet training dataset, called ImageNet+, as well as reinforced datasets CIFAR-100+, Flowers-102+, and Food-101+. Models trained with ImageNet+ are more accurate, robust, and calibrated, and transfer well to downstream tasks.
  arXiv  Detail & Related papers  (2023-03-15T23:10:17Z)
• 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)
• Network Augmentation for Tiny Deep Learning [73.57192520534585]
  We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks. We demonstrate the effectiveness of NetAug on image classification and object detection.
  arXiv  Detail & Related papers  (2021-10-17T18:48:41Z)
• High-Performance Large-Scale Image Recognition Without Normalization [34.58818094675353]
  Batch normalization is a key component of most image classification models, but it has many undesirable properties. We develop an adaptive gradient clipping technique which overcomes these instabilities, and design a significantly improved class of Normalizer-Free ResNets. Our models attain significantly better performance than their batch-normalized counterparts when finetuning on ImageNet after large-scale pre-training.
  arXiv  Detail & Related papers  (2021-02-11T18:23:20Z)
• Training EfficientNets at Supercomputer Scale: 83% ImageNet Top-1 Accuracy in One Hour [38.89981855438478]
  We present techniques to scale up the training of EfficientNets on TPU-v3 Pods with 2048 cores. We are able to train EfficientNet on ImageNet to an accuracy of 83% in 1 hour and 4 minutes.
  arXiv  Detail & Related papers  (2020-10-30T19:27:11Z)
• 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.