--- title: "Caffe: Convolutional Architecture for Fast — Jia 2014" description: "Deep convolutional networks had become the leading approach to visual recognition, but reproducing published results could take months." authors: ["Yangqing Jia", "Evan Shelhamer", "Jeff Donahue", "Sergey Karayev", "Jonathan Long", "Ross Girshick", "Sergio Guadarrama", "Trevor Darrell"] year: 2014 venue: "arXiv:1408.5093" source: "https://arxiv.org/abs/1408.5093" doi: "10.48550/arxiv.1408.5093" arxiv: "1408.5093" licence: "arXiv — non-exclusive licence to distribute" licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/jia-2014-caffe-convolutional-architecture-fast-feature/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/jia-2014-caffe-convolutional-architecture-fast-feature/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2014](https://md.research.elamur.ai/free/en/papers/2014/) / Caffe: Convolutional Architecture for Fast Feature Embedding # Caffe: Convolutional Architecture for Fast Feature Embedding **Authors:** Yangqing Jia, Evan Shelhamer, [Jeff Donahue](https://md.research.elamur.ai/free/en/authors/jeff-donahue/), Sergey Karayev, Jonathan Long, [Ross Girshick](https://md.research.elamur.ai/free/en/authors/ross-girshick/), [Sergio Guadarrama](https://md.research.elamur.ai/free/en/authors/sergio-guadarrama/), [Trevor Darrell](https://md.research.elamur.ai/free/en/authors/trevor-darrell/) · **Year:** 2014 · **Venue:** arXiv:1408.5093 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://arxiv.org/abs/1408.5093) · [PDF](https://arxiv.org/pdf/1408.5093) · [DOI 10.48550/arxiv.1408.5093](https://doi.org/10.48550/arxiv.1408.5093) · [arXiv 1408.5093](https://arxiv.org/abs/1408.5093) · [OpenAlex](https://openalex.org/W2950094539) **Citations:** 3752 citations (openalex-snapshot · 2026-10-14) · [312](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary Deep convolutional networks had become the leading approach to visual recognition, but reproducing published results could take months. Existing toolkits rarely combined fast execution with ready-made state-of-the-art models. The UC Berkeley team (BVLC) presents Caffe, an open-source deep learning framework written in C++. It uses CUDA for GPU acceleration and offers Python/Numpy and MATLAB bindings. Networks are declared in Protocol Buffer configuration files as arbitrary directed acyclic graphs of layers, which keeps the model definition independent of the executing code. A single call moves the same network between CPU and GPU. Layers exchange data through 4-dimensional "blobs" that handle host–device synchronization and allocate memory lazily. Every module has unit tests. Training relies on SGD with momentum, learning-rate schedules, snapshots and fine-tuning. Caffe ships reference models with recipes to reproduce them and handles over 40 million images per day on one GPU. Its speed, modularity and focus on reproducibility make it a practical shared base for research and industrial deployment. ## Key points - Throughput is about 2.5 ms per image (over 40M images/day) on a single NVIDIA K40 or Titan GPU. LevelDB plus Protocol Buffers storage reaches 150 MB/s on commodity machines. - Built-in layers include convolution, pooling, inner product, ReLU/logistic, local response normalization, element-wise operations, and softmax and hinge losses. The MNIST example is LeNet (`lenet_train.prototxt`). - The code is BSD-licensed on GitHub (BVLC/caffe). The reference models, such as the "AlexNet" ImageNet model and the R-CNN detector, are restricted to academic and non-commercial use. - Table 1 compares Caffe with cuda-convnet, Decaf, OverFeat, Theano/Pylearn2 and Torch7. Its distinguishing features are a pure C++ core with a CPU mode and off-the-shelf pretrained models. - Reported applications include: - R-CNN with Selective Search, top detection results on PASCAL VOC 2007–2012 and the ImageNet 2013 Detection challenge; - fine-tuning to all 10,000 ImageNet categories for open-vocabulary retrieval; - style recognition on the Flickr Style dataset. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Other](https://md.research.elamur.ai/free/en/shelves/other/) ## Cited by Cited by 312 papers of our library cite it (of the 140884 whose bibliographies we read); 13 of them have a page here, 299 not yet. - [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://md.research.elamur.ai/free/en/papers/abadi-2016-tensorflow-large-scale-machine-learning/) - [Guided Open Vocabulary Image Captioning with Constrained Beam Search](https://md.research.elamur.ai/free/en/papers/anderson-2017-guided-open-vocabulary-image-captioning/) - [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://md.research.elamur.ai/free/en/papers/anderson-2017-vision-language-navigation-interpreting-visually/) - [MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems](https://md.research.elamur.ai/free/en/papers/chen-2015-mxnet-flexible-efficient-machine-learning/) - [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://md.research.elamur.ai/free/en/papers/donahue-2014-long-term-recurrent-convolutional-networks/) - [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://md.research.elamur.ai/free/en/papers/howard-2017-mobilenets-efficient-convolutional-neural-networks/) - [Combining Language and Vision with a Multimodal Skip-gram Model](https://md.research.elamur.ai/free/en/papers/lazaridou-2015-combining-language-vision-multimodal-skip/) - [Merging Models with Fisher-Weighted Averaging](https://md.research.elamur.ai/free/en/papers/matena-2021-merging-models-fisher-weighted-averaging/) - [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://md.research.elamur.ai/free/en/papers/paszke-2019-pytorch-imperative-style-high-performance/) - [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://md.research.elamur.ai/free/en/papers/ronneberger-2015-u-net-convolutional-networks-biomedical/) - [Detecting Sarcasm in Multimodal Social Platforms](https://md.research.elamur.ai/free/en/papers/schifanella-2016-detecting-sarcasm-multimodal-social-platforms/) - [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://md.research.elamur.ai/free/en/papers/selvaraju-2016-grad-cam-visual-explanations-deep/) - [Black Holes and White Rabbits: Metaphor Identification with Visual Features](https://md.research.elamur.ai/free/en/papers/shutova-2016-black-holes-white-rabbits-metaphor/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{jia2014caffe, title = {{Caffe: Convolutional Architecture for Fast Feature Embedding}}, author = {Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick, Ross and Guadarrama, Sergio and Darrell, Trevor}, year = {2014}, doi = {10.48550/arxiv.1408.5093}, eprint = {1408.5093}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.1408.5093} } ``` - [← previous Building a reference lexicon for countability in English](https://md.research.elamur.ai/free/en/papers/lingbulk-2014-kiss-building-reference-lexicon-countability-english/) - [next → Chinese Irony Corpus Construction and Ironic Structure Analysis](https://md.research.elamur.ai/free/en/papers/tang-2014-chinese-irony-corpus-construction-ironic/) - [↑ back to papers of 2014](https://md.research.elamur.ai/free/en/papers/2014/) ## References 11 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. R. Collobert, K. Kavukcuoglu, and C. Farabet. Torch7: A MATLAB-like environment for machine learning. In BigLearn, NIPS Workshop, 2011. [find](https://scholar.google.com/scholar?q=R%2E+Collobert%2C+K%2E+Kavukcuoglu%2C+and+C%2E+Farabet%2E+Torch7%3A+A+MATLAB%2Dlike+environment+for+machine+learning%2E+In+BigLearn%2C+NIPS+Workshop%2C+2011%2E) 2. J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell. Decaf: A deep convolutional activation feature for generic visual recognition. In ICML, 2014. [find](https://scholar.google.com/scholar?q=J%2E+Donahue%2C+Y%2E+Jia%2C+O%2E+Vinyals%2C+J%2E+Hoffman%2C+N%2E+Zhang%2C+E%2E+Tzeng%2C+and+T%2E+Darrell%2E+Decaf%3A+A+deep+convolutional+activation+feature+for+generic+visual+recognition%2E+In+ICML%2C+2014%2E) 3. R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR, 2014. [find](https://scholar.google.com/scholar?q=R%2E+Girshick%2C+J%2E+Donahue%2C+T%2E+Darrell%2C+and+J%2E+Malik%2E+Rich+feature+hierarchies+for+accurate+object+detection+and+semantic+segmentation%2E+In+CVPR%2C+2014%2E) [our card](https://md.research.elamur.ai/free/en/papers/girshick-2013-rich-feature-hierarchies-accurate-object/) 4. I. Goodfellow, D. Warde-Farley, P. Lamblin, V. Dumoulin, M. Mirza, R. Pascanu, J. Bergstra, F. Bastien, and Y. Bengio. Pylearn2: a machine learning research library. arXiv preprint 1308.4214, 2013. — [arXiv:1308.4214](https://arxiv.org/abs/1308.4214) [find](https://scholar.google.com/scholar?q=I%2E+Goodfellow%2C+D%2E+Warde%2DFarley%2C+P%2E+Lamblin%2C+V%2E+Dumoulin%2C+M%2E+Mirza%2C+R%2E+Pascanu%2C+J%2E+Bergstra%2C+F%2E+Bastien%2C+and+Y%2E+Bengio%2E+Pylearn2%3A+a+machine+learning+research+library%2E+arXiv+preprint+1308%2E4214%2C+2013%2E+%E2%80%94+) 5. S. Guadarrama, E. Rodner, K. Saenko, N. Zhang, R. Farrell, J. Donahue, and T. Darrell. Open-vocabulary object retrieval. In RSS, 2014. [find](https://scholar.google.com/scholar?q=S%2E+Guadarrama%2C+E%2E+Rodner%2C+K%2E+Saenko%2C+N%2E+Zhang%2C+R%2E+Farrell%2C+J%2E+Donahue%2C+and+T%2E+Darrell%2E+Open%2Dvocabulary+object+retrieval%2E+In+RSS%2C+2014%2E) 6. S. Karayev, M. Trentacoste, H. Han, A. Agarwala, T. Darrell, A. Hertzmann, and H. Winnemoeller. Recognizing image style. arXiv preprint 1311.3715, 2013. — [arXiv:1311.3715](https://arxiv.org/abs/1311.3715) [find](https://scholar.google.com/scholar?q=S%2E+Karayev%2C+M%2E+Trentacoste%2C+H%2E+Han%2C+A%2E+Agarwala%2C+T%2E+Darrell%2C+A%2E+Hertzmann%2C+and+H%2E+Winnemoeller%2E+Recognizing+image+style%2E+arXiv+preprint+1311%2E3715%2C+2013%2E+%E2%80%94+%5BarXiv%3A1311%2E3715%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1311%2E) 7. A. Krizhevsky. cuda-convnet. [https://code.google.com/p/cuda-convnet/](https://code.google.com/p/cuda-convnet/), 2012. [↗](https://code.google.com/p/cuda-convnet/) 8. A. Krizhevsky, I. Sutskever, and G. Hinton. ImageNet classification with deep convolutional neural networks. In NIPS, 2012. [find](https://scholar.google.com/scholar?q=A%2E+Krizhevsky%2C+I%2E+Sutskever%2C+and+G%2E+Hinton%2E+ImageNet+classification+with+deep+convolutional+neural+networks%2E+In+NIPS%2C+2012%2E) 9. P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun. Overfeat: Integrated recognition, localization and detection using convolutional networks. In ICLR, 2014. [find](https://scholar.google.com/scholar?q=P%2E+Sermanet%2C+D%2E+Eigen%2C+X%2E+Zhang%2C+M%2E+Mathieu%2C+R%2E+Fergus%2C+and+Y%2E+LeCun%2E+Overfeat%3A+Integrated+recognition%2C+localization+and+detection+using+convolutional+networks%2E+In+ICLR%2C+2014%2E) 10. J. Uijlings, K. van de Sande, T. Gevers, and A. Smeulders. Selective search for object recognition. IJCV, 2013. [find](https://scholar.google.com/scholar?q=J%2E+Uijlings%2C+K%2E+van+de+Sande%2C+T%2E+Gevers%2C+and+A%2E+Smeulders%2E+Selective+search+for+object+recognition%2E+IJCV%2C+2013%2E) 11. N. Zhang, M. Paluri, M. Ranzato, T. Darrell, and L. Bourdev. Panda: Pose aligned networks for deep attribute modeling. In CVPR, 2014. [https://github.com/BVLC/caffe/http://caffe.berkeleyvision.org/](https://github.com/BVLC/caffe/http://caffe.berkeleyvision.org/) [↗](https://github.com/BVLC/caffe/http://caffe.berkeleyvision.org/)