Ben Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jeǵou, Matthijs Douze
Paper appears method- or tooling-adjacent to AI workflows with partial ecosystem coverage.
We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly parallel processing hardware. We revisit principles from the extensive literature on convolutional neural networks to apply them to transformers, in particular activation maps wit ...
h decreasing resolutions. We also introduce the attention bias, a new way to integrate positional information in vision transformers. As a result, we propose LeVIT: a hybrid neural network for fast inference image classification. We consider different measures of efficiency on different hardware platforms, so as to best reflect a wide range of application scenarios. Our extensive experiments empirically validate our technical choices and show they are suitable to most architectures. Overall, LeViT significantly outperforms existing convnets and vision transformers with respect to the speed/accuracy tradeoff. For example, at 80% ImageNet top-1 accuracy, LeViT is 5 times faster than EfficientNet on CPU. We release the code at https://github.com/facebookresearch/LeViT
Some benchmark signal exists in the extracted evidence, but it is not structured strongly enough yet for a confident benchmark decision.
We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime.
cmhungsteve/Awesome-Transformer-Attention is the closest maintained adjacent implementation (Matches contextual method/domain keyword: transformer). It is not paper-verified; validate algorithm and evaluation setup against the paper before trusting reported metrics. Community adoption signal: 5041 GitHub stars.
Hardware Notes
Expect multi-day setup/compute for meaningful reproduction based on current guidance.
Evidence graph: 3 refs, 3 links.
Utility signals: depth 100/100, grounding 85/100, status high.
Compare maintenance quality, reproducibility coverage, and evidence confidence before choosing a reproduction baseline.
Strong overlap with paper title keywords · Community adoption signal (623 stars)
Risk flags
There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.
Hardware requirements
No verified implementation available
Framework baselines
Modern transformer training baseline.
Reference transformer building block implementation.
These are not paper-verified. Use them as reference points when no direct implementation is available.
Matches contextual method/domain keyword: transformer
Matches contextual method/domain keyword: transformer
No additional verified repositories beyond the primary recommendation.
These repositories had low-confidence matching signals and are hidden by default.
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:
Models
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.
91
Citations
66
References
Tasks
Computer science, Inference, Exploit, Convolutional neural network, Artificial neural network, Computer engineering, Code (set theory)
Methods
Transformer
Domains
Artificial intelligence, Machine learning, Computer Vision and Pattern Recognition
Evaluation & Human Feedback Data
Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.
Open in HFEPXExplore Similar Papers
Jump to Paper2Code search queries derived from this paper's research context.
Need human evaluators for your AI research? Scale annotation with expert AI Trainers.