Skip to content
OpenTrain AIFor AI Companies

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

Kai Han, Yunhe Wang, Qiulin Zhang, Wei Zhang, Chunjing Xu +1 morePublished Oct 28, 2020
DOI Publisher
Researcher verdict
Context only
Use as context only
Benchmark evidence
Thin evidence
Verify before relying
Time to first repro
A few days
Plan setup time
Risk flags
2
Review before use

Abstract

Domain fit: AI-adjacent · Paper appears method- or tooling-adjacent to AI workflows with partial ecosystem coverage.

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.

Results and benchmarks

Freshness tier: cold
To obtain excellent deep neural architectures, a series of techniques are carefully designed in EfficientNets.

Implementation

No direct implementation yet

Maintained implementation evidence is not confirmed for this paper yet.

Use the implementation status and reproduction sections for the current action plan.

Implementation evidence summary
Confidence: low

Recommendation evidence is currently too limited for a maintained-repo choice. Use Implementation Status and Reproduction Path for a practical baseline plan.

Reproduction risks
  • Estimate is based on paper-only reproduction flow

Reproduction readiness

Time to first repro: days
Last checked: Aug 23, 2026

No repo

No verified implementation available

  • No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.

Hardware requirements

  • Expect multi-day setup/compute for meaningful reproduction based on current guidance.

Hugging Face artifacts

No trustworthy direct or curated related Hugging Face artifacts were found yet. Use targeted searches to quickly locate candidate models, datasets, and demos.

Tip: start with models, then check datasets and spaces if you need evaluation data or demos.

Research context

37

Citations

56

References

Tasks

Cube (algebra), Resolution (logic), Computer graphics (images), Geometry, Computer science, Physical Sciences

Methods

None detected

Domains

Mathematics, Computer Vision and Pattern Recognition

Evaluation and human feedback data

Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.

Open in HFEPX
Explore similar papers