BranchyNet: Fast inference via early exiting from deep neural networks
The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
Deep neural networks are state of the art methods for many learning tasks due to their ability to extract increasingly better features at each network layer. However, the improved performance of additional layers in a deep network comes at the cost of added latency and energy usage in feedforward inference. As networks continue to get deeper and larger, these costs become more prohibitive for real-time and energy-sensitive applications. To address this issue, we present BranchyNet, a novel deep network architecture that is augmented with additional side branch classifiers. The architecture allows prediction results for a large portion of test samples to exit the network early via these branches when samples can already be inferred with high confidence. BranchyNet exploits the observation that features learned at an early layer of a network may often be sufficient for the classification of many data points. For more difficult samples, which are expected less frequently, BranchyNet will use further or all network layers to provide the best likelihood of correct prediction. We study the BranchyNet architecture using several well-known networks (LeNet, AlexNet, ResNet) and datasets (MNIST, CIFAR10) and show that it can both improve accuracy and significantly reduce the inference time of the network.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“In contrast, EE-ensemble method employs only half as many exits (only EEs) compared to QUTE, and the EE's regularization effect helps network accuracy (Teerapittayanon et al., 2016).”
From QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoring (2024) · cites this paper as Teerapittayanon et al., 2016
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
(2014) · Cited by 33,419
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
(2010) · Cited by 14,134
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Deep Networks with Stochastic Depth
Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K. Q. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_39 · Cited by 2,104
Buciluǎ, C., Caruana, R., & Niculescu-Mizil, A. (2006) · Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1150402.1150464 · Cited by 2,068
Towards Open Set Deep Networks
Bendale, A., & Boult, T. E. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.173 · Cited by 1,799
Learning both Weights and Connections for Efficient Neural Networks
Han, S., Pool, J., Tran, J., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1506.02626 · Cited by 1,481
LeCun, Y., Bottou, L., Orr, G., & Müller, K. (1998) · neural information processing systems · Cited by 1,333
LeCun, Y. A., Bottou, L., Orr, G. B., & Müller, K.-R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_3 · Cited by 1,264
Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile ApplicationsPreprint
Kim, Y., Park, E., Yoo, S., Choi, T., Lu, Y., & Shin, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.06530 · Cited by 920
Fast Algorithms for Convolutional Neural Networks
Lavin, A., & Gray, S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.435 · Cited by 915
Srivastava, R. K., Greff, K., & Schmidhuber, J. (2015) · arXiv · doi:10.48550/arxiv.1505.00387 · Cited by 912
(2011) · Cited by 713
Towards Open World Recognition
Bendale, A., & Boult, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298799 · Cited by 529
Fast Training of Convolutional Networks through FFTs
Mathieu, M., Henaff, M., & LeCun, Y. (2014) · International Conference on Learning Representations · Cited by 347
Towards Open World Recognition
Bendale, A., & Boult, T. E. (2016) · Cited by 279
Fast Training of Convolutional Networks through FFTs
Mathieu, M., Henaff, M., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.5851 · Cited by 273
Deep Networks with Stochastic DepthPreprint
Huang, G. M., Sun, Y., Liu, Z., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.09382 · Cited by 272
Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition
Panda, P., Sengupta, A., & Roy, K. (2016) · Design, Automation, and Test in Europe · doi:10.3850/9783981537079_0819 · Cited by 235
Meta-Recognition: The Theory and Practice of Recognition Score Analysis
Scheirer, W. J., Rocha, A., Micheals, R. J., & Boult, T. E. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.54 · Cited by 211
Fast Algorithms for Convolutional Neural NetworksPreprint
Lavin, A., & Gray, S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.09308 · Cited by 124
Predicting Failures of Vision Systems
Zhang, P., Wang, J., Farhadi, A., Hebert, M., & Parikh, D. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.456 · Cited by 122
Cited by
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455
“BranchyNet [87] is a programming framework that implements the model early-exit mechanism.”
MethodNAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
Ghiasi, G., Lin, T.-Y., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00720 · Cited by 2,099
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
Pre-trained models for natural language processing: A survey
Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., & Huang, X. (2020) · Science China Technological Sciences · doi:10.1007/s11431-020-1647-3 · Cited by 1,591
“The idea of early exit is first applied in computer vision, such as BranchyNet [182] and Shallow-Deep Network [183].”
MethodDeep Learning With Edge Computing: A Review
Chen, J., & Ran, X. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2921977 · Cited by 1,540
Metadata
- Authors
- Teerapittayanon, S., McDanel, B., & Kung, H. T.
- Affiliations
- Harvard University (US)
- Venue
- 2016 23rd International Conference on Pattern Recognition (ICPR)
- Publisher
- IEEE
- Published
- 2016-12
- Pages
- 2464-2469
- ISSN
- 1041-3278 (ISSN-L)
- OpenAlex
- W2962677625
- Cited by
- 1,326
- References
- 27
- Citations by year
- 2026: 182 · 2025: 195 · 2024: 184 · 2023: 219 · 2022: 160 · 2021: 161 · 2020: 119 · 2019: 69 · 2018: 23 · 2017: 12 · 2016: 2
- FWCI
- 12.26
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition (publishedVersion)
- Funders
- Intel Corporation
- Nvidia
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Keywords
- early exit, inference acceleration, deep learning architectures, inference latency reduction, energy-efficient inference, image classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.