Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections - one between each layer and its subsequent layer - our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less computation to achieve high performance.
*Models with * are converted from [pytorch](https://pytorch.org/vision/stable/models.html), guided by [original repo](https://github.com/liuzhuang13/DenseNet). The config files of these models are only for inference. We don't ensure these config files' training accuracy and welcome you to contribute your reproduction results.*
## Citation
```bibtex
@misc{https://doi.org/10.48550/arxiv.1608.06993,
doi={10.48550/ARXIV.1608.06993},
url={https://arxiv.org/abs/1608.06993},
author={Huang, Gao and Liu, Zhuang and van der Maaten, Laurens and Weinberger, Kilian Q.},
keywords={Computer Vision and Pattern Recognition (cs.CV), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
> [EfficientFormer: Vision Transformers at MobileNet Speed](https://arxiv.org/abs/2206.01191)
<!-- [ALGORITHM] -->
## Abstract
Vision Transformers (ViT) have shown rapid progress in computer vision tasks, achieving promising results on various benchmarks. However, due to the massive number of parameters and model design, e.g., attention mechanism, ViT-based models are generally times slower than lightweight convolutional networks. Therefore, the deployment of ViT for real-time applications is particularly challenging, especially on resource-constrained hardware such as mobile devices. Recent efforts try to reduce the computation complexity of ViT through network architecture search or hybrid design with MobileNet block, yet the inference speed is still unsatisfactory. This leads to an important question: can transformers run as fast as MobileNet while obtaining high performance? To answer this, we first revisit the network architecture and operators used in ViT-based models and identify inefficient designs. Then we introduce a dimension-consistent pure transformer (without MobileNet blocks) as a design paradigm. Finally, we perform latency-driven slimming to get a series of final models dubbed EfficientFormer. Extensive experiments show the superiority of EfficientFormer in performance and speed on mobile devices. Our fastest model, EfficientFormer-L1, achieves 79.2% top-1 accuracy on ImageNet-1K with only 1.6 ms inference latency on iPhone 12 (compiled with CoreML), which runs as fast as MobileNetV2×1.4 (1.6 ms, 74.7% top-1), and our largest model, EfficientFormer-L7, obtains 83.3% accuracy with only 7.0 ms latency. Our work proves that properly designed transformers can reach extremely low latency on mobile devices while maintaining high performance.
*Models with * are converted from the [official repo](https://github.com/snap-research/EfficientFormer). The config files of these models are only for inference. We don't ensure these config files' training accuracy and welcome you to contribute your reproduction results.*
## Citation
```bibtex
@misc{https://doi.org/10.48550/arxiv.2206.01191,
doi={10.48550/ARXIV.2206.01191},
url={https://arxiv.org/abs/2206.01191},
author={Li, Yanyu and Yuan, Geng and Wen, Yang and Hu, Eric and Evangelidis, Georgios and Tulyakov, Sergey and Wang, Yanzhi and Ren, Jian},
keywords={Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
title={EfficientFormer: Vision Transformers at MobileNet Speed},
> [Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946v5)
<!-- [ALGORITHM] -->
## Abstract
Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. We demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. To go even further, we use neural architecture search to design a new baseline network and scale it up to obtain a family of models, called EfficientNets, which achieve much better accuracy and efficiency than previous ConvNets. In particular, our EfficientNet-B7 achieves state-of-the-art 84.3% top-1 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet. Our EfficientNets also transfer well and achieve state-of-the-art accuracy on CIFAR-100 (91.7%), Flowers (98.8%), and 3 other transfer learning datasets, with an order of magnitude fewer parameters.
In the result table, AA means trained with AutoAugment pre-processing, more details can be found in the [paper](https://arxiv.org/abs/1805.09501), and AdvProp is a method to train with adversarial examples, more details can be found in the [paper](https://arxiv.org/abs/1911.09665).
Note: In MMClassification, we support training with AutoAugment, don't support AdvProp by now.
*Models with * are converted from the [official repo](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet). The config files of these models are only for inference. We don't ensure these config files' training accuracy and welcome you to contribute your reproduction results.*
## Citation
```
@inproceedings{tan2019efficientnet,
title={Efficientnet: Rethinking model scaling for convolutional neural networks},
author={Tan, Mingxing and Le, Quoc},
booktitle={International Conference on Machine Learning},
