Going deeper with Image Transformers
Hugo Touvron, Matthieu Cord, Alexandre Sablayrolles, Gabriel Synnaeve, Hervé Jeǵou
Paper appears method- or tooling-adjacent to AI workflows with partial ecosystem coverage.
Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of image transformers has been little studied so far. In this work, we build and optimize deeper transformer networks for image classification. In particular, we investigate the interplay of architecture and optimization of such de ...
dicated transformers. We make two transformers architecture changes that significantly improve the accuracy of deep transformers. This leads us to produce models whose performance does not saturate early with more depth, for instance we obtain 86.5% top-1 accuracy on Imagenet when training with no external data, we thus attain the current SOTA with less FLOPs and parameters. Moreover, our best model establishes the new state of the art on Imagenet with Reassessed labels and Imagenet-V2 / match frequency, in the setting with no additional training data. We share our code and models.
Results & Benchmarks
Some benchmark signal exists in the extracted evidence, but it is not structured strongly enough yet for a confident benchmark decision.
Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks.
Implementation Evidence Summary
OATML/non-parametric-transformers 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: 417 GitHub stars.
Reproduction Risks
- Adjacent implementations are not paper-verified
- Recommended repository is adjacent and not paper-verified.
- Adjacent implementation match confidence is low.
Hardware Notes
Expect multi-day setup/compute for meaningful reproduction based on current guidance.
Evidence disclosure
Evidence graph: 3 refs, 3 links.
Utility signals: depth 100/100, grounding 85/100, status high.
Implementation Status
There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.
- No maintained paper-verified implementation was found; start with the closest related repositories below.
- Compare repo methods against the paper equations/algorithm before trusting metrics.
- Create a minimal baseline implementation from the paper and use adjacent repos as references.
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.
Framework baselines
- Hugging Face Transformers training guide
Modern transformer training baseline.
- PyTorch nn.Transformer docs
Reference transformer building block implementation.
Closest related implementations
These are not paper-verified. Use them as reference points when no direct implementation is available.
- OATML/non-parametric-transformersAdjacentConfidence: LowStars: 417
Matches contextual method/domain keyword: transformer
- danderfer/Comp_Sci_Sem_2AdjacentConfidence: LowStars: 180
Matches contextual method/domain keyword: transformer
- mhuzaifadev/deep-learning-masterclassAdjacentConfidence: LowStars: 52
Matches contextual method/domain keyword: transformer
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:
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.
Research context
77
Citations
127
References
Tasks
FLOPS, Computer science, Convolutional neural network, Pattern recognition (psychology), Physical Sciences
Methods
Transformer, Architecture
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.
Related papers
-
Search on Paper2Code
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (2021) Semantic similarity
-
Search on Paper2Code
Training data-efficient image transformers & distillation through attention (2020) Semantic similarity
-
Search on Paper2Code
Deep Residual Learning for Image Recognition (2016) Semantic similarity
-
Search on Paper2Code
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet (2021) Semantic similarity
-
Search on Paper2Code
ImageNet: A large-scale hierarchical image database (2009) Semantic similarity
Need human evaluators for your AI research? Scale annotation with expert AI Trainers.