SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Forrest Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer
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 bandwi ...
dth 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 & Benchmarks
Some benchmark signal exists in the extracted evidence, but it is not structured strongly enough yet for a confident benchmark decision.
Recent research on deep neural networks has focused primarily on improving accuracy.
Implementation Evidence Summary
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
Hardware Notes
Expect multi-day setup/compute for meaningful reproduction based on current guidance.
Evidence disclosure
Evidence graph: 2 refs, 1 links.
Utility signals: depth 85/100, grounding 58/100, status medium.
Implementation Status
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: Learning Multiple Layers of Features from Tiny Images.
- Track assumptions and missing details in an experiment log before coding.
Reproduction readiness
Hardware requirements
- Expect multi-day setup/compute for meaningful reproduction based on current guidance.
No verified implementation available
- · No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.
Hugging Face artifacts
No trustworthy direct or curated related Hugging Face artifacts were found yet.
Continue with targeted Hugging Face searches derived from the paper title and method context:
Tip: start with models, then check datasets/spaces if you need evaluation data or demos.
Direct artifact matches are currently sparse. Use targeted Hugging Face searches to quickly locate candidate models, datasets, and demos.
Research context
5,925
Citations
40
References
Tasks
Computer science, Bandwidth (computing), Deep neural networks, Server, Cloud computing, Artificial neural network, Real-time computing
Methods
None detected
Domains
Artificial intelligence, Computer Vision and Pattern Recognition
Explore Similar Papers
Jump to Paper2Code search queries derived from this paper's research context.
Related papers
-
Search on Paper2Code
Learning Multiple Layers of Features from Tiny Images (2024) Semantic similarity
-
Search on Paper2Code
SSD: Single Shot MultiBox Detector (2016) Semantic similarity
-
Search on Paper2Code
Densely Connected Convolutional Networks (2017) Semantic similarity
-
Search on Paper2Code
MobileNetV2: Inverted Residuals and Linear Bottlenecks (2018) Semantic similarity
Need human evaluators for your AI research? Scale annotation with expert AI Trainers.