# Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets

arXiv: https://arxiv.org/abs/2010.14819 · HTML: https://mlsanity.com/paper/2010.14819/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2020.

## Built on by (most cited first, 30 of 49)

- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Mobile-Former: Bridging MobileNet and Transformer](https://mlsanity.com/paper/2108.05895/) (2021)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [MobileOne: An Improved One millisecond Mobile Backbone](https://mlsanity.com/paper/2206.04040/) (2022)
- [MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning](https://mlsanity.com/paper/2110.15352/) (2021)
- [TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation](https://mlsanity.com/paper/2204.05525/) (2022)
- [Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks](https://mlsanity.com/paper/2201.03299/) (2022)
- [Does progress on ImageNet transfer to real-world datasets?](https://mlsanity.com/paper/2301.04644/) (2023)
- [Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning](https://mlsanity.com/paper/2210.01035/) (2022)
- [EdgeFace: Efficient Face Recognition Model for Edge Devices](https://mlsanity.com/paper/2307.01838/) (2023)
- [AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models](https://mlsanity.com/paper/2107.13686/) (2021)
- [MicroNet: Improving Image Recognition with Extremely Low FLOPs](https://mlsanity.com/paper/2108.05894/) (2021)
- [BCNet: Searching for Network Width with Bilaterally Coupled Network](https://mlsanity.com/paper/2105.10533/) (2021)
- [On the Effect of Pruning on Adversarial Robustness](https://mlsanity.com/paper/2108.04890/) (2021)
- [CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters](https://mlsanity.com/paper/2203.15331/) (2022)
- [Efficient Modulation for Vision Networks](https://mlsanity.com/paper/2403.19963/) (2024)
- [The 3D-PC: a benchmark for visual perspective taking in humans and machines](https://mlsanity.com/paper/2406.04138/) (2024)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [An overview of artificial intelligence techniques for diagnosis of Schizophrenia based on magnetic resonance imaging modalities: Methods, challenges, and future works](https://mlsanity.com/paper/2103.03081/) (2021)
- [MoCoViT: Mobile Convolutional Vision Transformer](https://mlsanity.com/paper/2205.12635/) (2022)
- [CP3: Channel Pruning Plug-in for Point-based Networks](https://mlsanity.com/paper/2303.13097/) (2023)
- [SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data](https://mlsanity.com/paper/2308.14852/) (2023)
- [SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers](https://mlsanity.com/paper/2311.03747/) (2023)
- [Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment](https://mlsanity.com/paper/2403.19490/) (2024)
- [GhostSR: Learning Ghost Features for Efficient Image Super-Resolution](https://mlsanity.com/paper/2101.08525/) (2021)
- [Dynamic ConvNets on Tiny Devices via Nested Sparsity](https://mlsanity.com/paper/2203.03324/) (2022)
- [FalconNet: Factorization for the Light-weight ConvNets](https://mlsanity.com/paper/2306.06365/) (2023)
- [Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs](https://mlsanity.com/paper/2107.03815/) (2021)
- [YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems](https://mlsanity.com/paper/2307.13901/) (2023)

## Abstract (arXiv)

To obtain excellent deep neural architectures, a series of techniques are carefully designed in EfficientNets. The giant formula for simultaneously enlarging the resolution, depth and width provides us a Rubik's cube for neural networks. So that we can find networks with high efficiency and excellent performance by twisting the three dimensions. This paper aims to explore the twisting rules for obtaining deep neural networks with minimum model sizes and computational costs. Different from the network enlarging, we observe that resolution and depth are more important than width for tiny networks. Therefore, the original method, i.e., the compound scaling in EfficientNet is no longer suitable. To this end, we summarize a tiny formula for downsizing neural architectures through a series of smaller models derived from the EfficientNet-B0 with the FLOPs constraint. Experimental results on the ImageNet benchmark illustrate that our TinyNet performs much better than the smaller version of EfficientNets using the inversed giant formula. For instance, our TinyNet-E achieves a 59.9% Top-1 accuracy with only 24M FLOPs, which is about 1.9% higher than that of the previous best MobileNetV3 with similar computational cost. Code will be available at https://github.com/huawei-noah/ghostnet/tree/master/tinynet_pytorch, and https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/cv/tinynet.