The DOI matches its Crossref record; 23 of the 24 references it cites were found in a registry or an index.
EPNet: Learning to Exit with Flexible Multi-Branch Network
Abstract
Dynamic inference is an emerging technique that reduces the computational cost of deep neural network under resource-constrained scenarios, such as inference on mobile devices. One way to achieve dynamic inference is to leverage multi-branch neural networks that apply different computation on input data by following different branches. Conventional research on multi-branch neural networks mainly targeted at improving the accuracy of each branch, and use manually designed rules to decide which input follows which branch of the network. Furthermore, these networks often provide a small number of exits, limiting their ability to adapt to external changes. In this paper, we investigate the problem of designing a flexible multi-branch network and early-exiting policies that can adapt to the resource consumption to individual inference request without impacting the inference accuracy. We propose a lightweight branch structure that also provides fine-grained flexibility for early-exiting and leverage Markov decision process (MDP) to automatically learn the early-exiting policies. Our proposed model, EPNet, was effective in reducing inference cost without impacting accuracy by choosing the most suitable branch exit. We also observe that EPNet achieved 3% higher accuracy with an inference budget, compared to state-of-the-art approaches.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Deep learning models often exhibit redundancy, where shallower layers suffice to classify 'easy' input samples accurately, while deeper layers are only necessary for more complex or ambiguous inputs [31].”
From A cascade framework for on-device uncertainty-aware event detection on microcontrollers (2026) · cites this paper as [31]
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
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
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
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
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00716 · Cited by 9,982
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201 · cited 8×
“Deep convolutional neural networks (CNNs) have achieved good accuracy on computer vision tasks such as image classification [8, Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or comme…”
MethodInfluentialSimple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
Williams, R. J. (1992) · Machine Learning · doi:10.1007/bf00992696 · Cited by 3,416
Recurrent Models of Visual Attention
Mnih, V., Heess, N., Graves, A., & Kavukcuoglu, K. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.6247 · Cited by 2,568
Research works printed but not linked: 1
- Song Han Jeff Pool John Tran and William Dally. 2015. Learning both weights and connections for efficient neural network. InAdvances in Neural Information Processing Systems 28 (NeurIPS'15). 1135--1143. Song Han Jeff Pool John Tran and William Dally. 2015. Learning both weights and connections for efficient neural network. InAdvances in Neural Information Processing Systems 28 (NeurIPS'15). 1135--1143.
Cited by
Dynamic Neural Networks: A Survey
Han, Y., Huang, G., Song, S., Yang, L., Wang, H., & Wang, Y. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3117837 · Cited by 848
Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
Laskaridis, S., Kouris, A., & Lane, N. D. (2021) · International Workshop on Embedded and Mobile Deep Learning (EMDL) · doi:10.1145/3469116.3470012 · Cited by 203
Early-Exit Deep Neural Network - A Comprehensive Survey
Haseena Rahmath, P., Srivastava, V., Chaurasia, K., Pacheco, R. G., & Couto, R. S. (2024) · ACM Computing Surveys · doi:10.1145/3698767 · Cited by 160
Dynamic Early Exit Scheduling for Deep Neural Network Inference through Contextual Bandits
Ju, W., Bao, W., Ge, L., & Yuan, D. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482335 · Cited by 39
Steering Angle-Guided Multimodal Fusion Lane Detection for Autonomous Driving
Gong, Y., Zhang, X., Lu, J., Jiang, X., Wang, Z., Liu, H., Li, Z., Wang, L., Yang, Q., & Wu, X. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3507536 · Cited by 26
Metadata
- Authors
- Dai, X., Kong, X., & Guo, T.
- Affiliations
- Worcester Polytechnic Institute (US)
- Venue
- Proceedings of the 29th ACM International Conference on Information & Knowledge Management
- Publisher
- ACM
- Published
- 2020-10-19
- Pages
- 235-244
- ISSN
- 2155-0751 (ISSN-L)
- OpenAlex
- W3094307698
- Cited by
- 48
- References
- 24
- Citations by year
- 2026: 6 · 2025: 9 · 2024: 14 · 2023: 10 · 2022: 4 · 2021: 5
- FWCI
- 1.47
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Conference on Information and Knowledge Management (CIKM) (publishedVersion)
- Funders
- NSF (CNS-1815619)
- 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 › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- dynamic inference, multi-branch network, Markov decision process, resource-constrained inference, mobile devices, inference cost reduction
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: EPNet: Learning to Exit with Flexible Multi-Branch Network. https://app.cochat.ai/papers/10.1145/3340531.3411973
- The paper
- Dai, X., Kong, X., & Guo, T. (2020). EPNet: Learning to Exit with Flexible Multi-Branch Network. Proceedings of the 29th ACM International Conference on Information & Knowledge Management. https://doi.org/10.1145/3340531.3411973
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.