SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Abstract
Domain fit: AI-adjacent · Paper appears method- or tooling-adjacent to AI workflows with partial ecosystem coverage.
Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet). The SqueezeNet architecture is available for download here: https://github.com/DeepScale/SqueezeNet
Results and benchmarks
Recent research on deep neural networks has focused primarily on improving accuracy.
Benchmark evidence is limited
Evidence graph: 2 refs, 1 links.
Utility signals: depth 85/100, grounding 58/100, status medium.
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.
No verified maintained repo yet
There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.
- No direct maintained implementation was found. Use the paper PDF and citation graph to design a baseline reproduction.
- Start from related paper: QuickNet: Maximizing Efficiency and Efficacy in Deep Architectures.
- Start from this likely method family: model compression.
Time to first repro: a few days
Recommendation evidence is currently too limited for a maintained-repo choice. Use Implementation Status and Reproduction Path for a practical baseline plan.
- Estimate is based on paper-only reproduction flow
Reproduction readiness
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
6,201
Citations
0
References
Tasks
Computer science, Econometrics, Environmental science, Statistics, SqueezeNet, lightweight neural networks, ImageNet classification, parameter reduction
Methods
model compression, model size reduction
Domains
Mathematics, Computer Vision and Pattern Recognition
Related papers
- QuickNet: Maximizing Efficiency and Efficacy in Deep ArchitecturesSearch on Paper2Code
2017 · Semantic similarity
- SlimNets: An Exploration of Deep Model Compression and AccelerationSearch on Paper2Code
2018 · Semantic similarity
- Toward Compact Parameter Representations for Architecture-Agnostic Neural Network CompressionSearch on Paper2Code
2021 · Semantic similarity
- Model Compression and Acceleration for Deep Neural Networks: The Principles, Progress, and ChallengesSearch on Paper2Code
2018 · Semantic similarity
- A Deep Neural Network Compression Pipeline: Pruning, Quantization, Huffman EncodingSearch on Paper2Code
2015 · Semantic similarity
- SqueezeNet: A Lightweight CNN Architecture Deep Learning with Fewer ParametersSearch on Paper2Code
2025 · Semantic similarity
Jump to Paper2Code search queries derived from this paper's research context.