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
Cited by
Items 901–1,000 of 1,000
Who Needs Decoders? Efficient Estimation of Sequence-Level Attributes with Proxies
Fathullah, Y., Radmard, P., Liusie, A., & Gales, M. (2024) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2024.eacl-long.89 · Cited by 5
Seethevoice: Learning from Music to Visual Storytelling of Shots
Wei, W.-L., Lin, J., Liu, T.-L., Yang, Y., Wang, H., Tyan, H.-R., & Liao, H.-Y. M. (2018) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486496 · Cited by 5
Once For All Skip: Efficient Adaptive Deep Neural Networks
Yang, Y., Liu, D., Fang, H., Huang, Y.-X., Sun, Y., & Zhang, Z. (2022) · Design, Automation, and Test in Europe · doi:10.23919/date54114.2022.9774567 · Cited by 5
Action Recognition With Motion Diversification and Dynamic Selection
Zhuang, P., Guo, Y., Yu, Z., Zhou, L., Bai, L., Liang, D., Wang, Z., Wang, Y., & Ouyang, W. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3189811 · Cited by 5
Shen, B., Lin, Z., Liu, Y., Liu, Z., Wang, L., & Wang, W. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.112 · Cited by 5
OPA: One-Predict-All For Efficient Deployment
Guo, J., Xia, S., & Peng, C. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10228928 · Cited by 5
Fast and accurate image recognition using Deeply-Fused Branchy Networks
Huang, M.-Y., Lai, C.-H., & Chen, S. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296808 · Cited by 5
Gacoin, V., Kolar, A., Ren, C., & Guinvarc’h, R. (2019) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2019.8702672 · Cited by 5
SIEVE: Speculative Inference on the Edge with Versatile Exportation
Zamirai, B., Latifi, S., Zamirai, P., & Mahlke, S. A. (2020) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac18072.2020.9218698 · Cited by 5
ECNet: A Fast, Accurate, and Lightweight Edge-Cloud Network System based on Cascading Structure
Hu, L., Wang, T., Watanabe, H., Enomoto, S., Shi, X., Sakamoto, A., & Eda, T. (2020) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce50665.2020.9291875 · Cited by 5
Wang, M., He, L., Lin, J. T., & Wang, Z. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3043329 · Cited by 5
Shi, L., Xu, Z., Shi, Y., Fan, Y., Ding, X., & Sun, Y. (2021) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-67537-0_15 · Cited by 5
Xarchakos, Y., & Koudas, N. (2021) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde51399.2021.00216 · Cited by 5
An Efficient Defect Detection System for Printed Circuit Boards with Edge-Cloud Fusion Computing
Wu, Y., Wang, J., & Chen, Y. (2021) · International Conference on Industrial Artificial Intelligence (IAI) · doi:10.1109/iai53119.2021.9619300 · Cited by 5
Sound Event Detection with Adaptive Frequency Selection
Wang, Z., Casebeer, J., Clemmitt, A., Tzinis, E., & Smaragdis, P. (2021) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa52581.2021.9632798 · Cited by 5
Kim, D., Nam, C.-M., Park, H., Jang, M., & Lee, K. J. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00327 · Cited by 5
Kundu, S., Sundaresan, S., Sridhar, S. N., Lu, S., Tang, H., & Beerel, P. A. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094760 · Cited by 5
Efficient Inference on Deep Neural Networks by Dynamic Representations and Decision Gates.Preprint
Shafiee, M. S., Shafiee, M. J., & Wong, A. M. (2018) · arXiv (Cornell University) · Cited by 5
ENAS4D: Efficient Multi-stage CNN Architecture Search for Dynamic InferencePreprint
Yuan, Z., Liu, X., Wu, B., & Sun, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09182 · Cited by 5
Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum LearningPreprint
Bakhtiarnia, A., Zhang, Q., & Iosifidis, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.10461 · Cited by 5
DNArch: Learning Convolutional Neural Architectures by BackpropagationPreprint
Romero, D. W., & Zeghidour, N. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.05400 · Cited by 5
Sensor-Aware Classifiers for Energy-Efficient Time Series Applications on IoT DevicesPreprint
Hussein, D., Nelson, L., & Bhat, G. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.08715 · Cited by 5
How to Train Your Multi-Exit Model? Analyzing the Impact of Training StrategiesPreprint
Kubaty, P., Wójcik, B., Krzepkowski, B., Michaluk, M., Trzcinski, T. P., Pomponi, J., & Adamczewski, K. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.14320 · Cited by 5
Energy-Aware Dynamic Neural InferencePreprint
Bullo, M., Jardak, S., Carnelli, P., & Gündüz, D. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.02471 · Cited by 5
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller OnesPreprint
Mofakhami, M., Bayat, R., Mitliagkas, I., Monteiro, J., & Zantedeschi, V. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.19325 · Cited by 5
Lamaakal, I., Yahyati, C., Makkaoui, K. E., Ouahbi, I., & Maleh, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.12905 · Cited by 5
From Models to Systems: A Comprehensive Survey of Efficient Multimodal LearningPreprint
Wang, P., Song, S., Ji, H., Cao, S., Yu, H., Liu, Z., Yang, H., Lin, Y., Chen, B., Bansal, M., et al. (2025) · doi:10.36227/techrxiv.176704030.08713592/v1 · Cited by 5
ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic InferencePreprint
Hojjat, A., Haberer, J., Pirk, S., & Landsiedel, O. (2025) · arXiv (Cornell University) · doi:10.15480/882.16505 · Cited by 5
Domain-Adaptive Online Active Learning for Real-Time Intelligent Video Analytics on Edge Devices
Boldo, M., De Marchi, M., Martini, E., Aldegheri, S., & Bombieri, N. (2024) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2024.3453188 · Cited by 4
“Examples are model compression techniques, such as neural network pruning [5], quantization [6], compact network design [7], as well as strategies like early exit [8].”
MethodQUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoring
Ghanathe, N. P., & Wilton, S. J. E. (2024) · arXiv · doi:10.48550/arxiv.2404.12599 · Cited by 4
DCentNet: Decentralized multistage biomedical signal classification using early exits
Li, X., Huang, B., Cardiff, B., & John, D. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.107468 · Cited by 4
Enhance UWB Performance Using Dynamic AI-Enabled Approach
He, X., Meng, X., Mo, L., Yang, F., Zhang, Y., & Wu, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3614999 · Cited by 4
Allen, J. S., & Hatfield, M. S. (2025) · Finance and Economics Discussion Series · doi:10.17016/feds.2025.092 · Cited by 4
SEEB-GPU: Early-Exit Aware Scheduling and Batching for Edge GPU Inference
Subramaniyan, S., Joshi, R., Wang, X., & Brocanelli, M. (2025) · ACM/IEEE Symposium on Edge Computing (SEC) · doi:10.1145/3769102.3772715 · Cited by 4
Learning spatio-temporal consistency in spiking neural networks by self-distillation
Zuo, L., Ding, Y., Jing, M., Yang, K., & Deng, H. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113108 · Cited by 4
Phoenix: Thermal-Aware On-Device Inference of Multi-Instance DNNs for Mobile Video Applications
Jeon, S., Kim, J., Lee, J., & Cha, H. (2026) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3793860 · Cited by 4
Harnessing Input-Adaptive Inference for Efficient VLN
Kang, D., Perincherry, A., Coalson, Z., Gabriel, A., Lee, S., & Hong, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00770 · Cited by 4
: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
Huang, H., Huang, J., Wan, Z., Zheng, X., Ji, R., & Luo, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37461-5_1 · Cited by 5
Exploiting the Common Case When Accelerating Input-Dependent Stream Processing by FPGA
Zhao, Z., Melber, J., Sahay, S., Obla, S., Nurvitadhi, E., & Hoe, J. C. (2022) · IEEE Transactions on Computers · doi:10.1109/tc.2022.3200576 · Cited by 4
Self-supervised efficient sample weighting for multi-exit networks
Liu, K., & Seungbin, M. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.111003 · Cited by 4
Bueno, A., Rubio, B., Martín, C., & Díáz, M. (2024) · Software Practice and Experience · doi:10.1002/spe.3318 · Cited by 4
CASNN: Continuous Adaptive SNN for Human Activity Recognition
Fang, Z., Li, J., & Wang, W. (2024) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea61579.2024.10665045 · Cited by 4
ACE: Efficient GPU Kernel Concurrency for Input-Dependent Irregular Computational Graphs
Durvasula, S., Zhao, A., Kiguru, R., Guan, Y., Chen, Z., & Vijaykumar, N. (2024) · International Conference on Parallel Architectures and Compilation Techniques (PACT) · doi:10.1145/3656019.3676897 · Cited by 4
Efficient Audio Deepfake Detection using WavLM with Early Exiting
Pimentel, A., Zhu, Y. M., Guimarães, H. R., & Falk, T. H. (2024) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs61860.2024.10810699 · Cited by 5
Computing Tasks Saving Schemes Through Early Exit in Edge Intelligence-Assisted Systems
Niu, X., Lv, X., Chen, W., Yu, C., & Jin, H. B. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3533098 · Cited by 4
Cloud-edge-end integrated Artificial intelligence based on ensemble learning
Gao, Z., Su, D., Liu, S., Zhang, Y., Wang, C., Zhang, C., Wang, X., & Taleb, T. (2025) · Computer Communications · doi:10.1016/j.comcom.2025.108103 · Cited by 4
An Elastic Federated Learning Collaboration Framework for Computing-Constrained IoT
Wang, H., Zou, G., Cao, K., Cui, Y., Wei, T., & Hu, S. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3593436 · Cited by 4
Wu, H.-S., Zhang, Z., & Papaefthymiou, M. C. (2018) · European Solid-State Circuits Conference (ESSCIRC) · doi:10.1109/esscirc.2018.8494279 · Cited by 4
SRCNN-PIL: Side Road Convolution Neural Network Based on Pseudoinverse Learning Algorithm
Mahmoud, M. A. B., Guo, P., Fathy, A., & Li, K. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10595-7 · Cited by 4
Adaptive Inference for Face Recognition leveraging Deep Metric Learning-enabled Early Exits
Passalis, N., & Tefas, A. (2021) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco54536.2021.9616231 · Cited by 4
Nousi, P., Tzelepi, M., Passalis, N., & Tefas, A. (2022) · Elsevier eBooks · doi:10.1016/b978-0-32-385787-1.00012-9 · Cited by 4
Kim, D., Park, H., Jang, M., & Lee, K. J. (2022) · Applied Sciences · doi:10.3390/app12136332 · Cited by 4
Luo, H., Tian, H., Zhang, P., Zhao, F., Zhou, M. C., & Sun, Y. (2021) · International Conference on Space-Air-Ground Computing (SAGC) · doi:10.1109/sagc52752.2021.00029 · Cited by 4
Towards Adversarial Robustness with Early Exit Ensembles
Qendro, L., & Mascolo, C. (2022) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc48229.2022.9871347 · Cited by 4
Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices
Saeed, A. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-17 · Cited by 4
Dispense Mode for Inference to Accelerate Branchynet
Liang, Z., & Zhou, Y. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897574 · Cited by 4
TinyOOD: Effective out-of-Distribution Detection for TinyML
Li, Y., Jia, J., Zuo, Y., & Zhu, W. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094746 · Cited by 4
Multi-exit DNN inference acceleration for intelligent terminal with heterogeneous processors
Zhang, J., Xin, W., Lv, D., Wang, J., Cai, G., & Dong, F. (2023) · Sustainable Computing Informatics and Systems · doi:10.1016/j.suscom.2023.100906 · Cited by 4
Efficient Federated Digital Twin Synchronization in Edge-Cloud Collaborative System
Kim, J.-W., Je-Gal, H., & Lee, H.-S. (2023) · IEEE International Conference on Metaverse Computing, Networking and Applications (MetaCom) · doi:10.1109/metacom57706.2023.00134 · Cited by 4
TRAIN: A Reinforcement Learning Based Timing-Aware Neural Inference on Intermittent Systems
Cheng, S.-T., Lim, W. S., Tu, C.-H., & Chang, Y.-H. (2023) · doi:10.1109/iccad57390.2023.10323634 · Cited by 4
MoTIF: a Method for Trustworthy Dynamic Multimodal Learning on Omics
Lu, Y., Peng, R., Jiang, B., & Wang, J. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10386044 · Cited by 4
Conditional Information Gain Trellis
Biçici, U. C., Meral, T. H. S., & Akarun, L. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2024.06.018 · Cited by 4
Self-supervised feature-gate coupling for dynamic network pruning
Shi, M., Liu, C., Jiao, J., & Ye, Q. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110594 · Cited by 4
Verma, P. R., Singh, N. P., & Pantola, D. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19670-2 · Cited by 4
Efficient Batched Inference in Conditional Neural Networks
Selvam, S., Nagarajan, A., & Raghunathan, A. (2024) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2024.3445263 · Cited by 4
Balancing Accuracy and Efficiency in Budget-Aware Early-Exiting Neural Networks
Addad, Y., Lechervy, A., & Jurie, F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78172-8_2 · Cited by 4
Resource‐adaptive and OOD‐robust inference of deep neural networks on IoT devices
Robertson, C., Tong, N. A., Nguyen, T. T., Nguyen, Q. V. H., & Jo, J. (2024) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12384 · Cited by 4
Early Exists Federated Learning (EEFL): Brining Training to the Edge
Douch, S., Abid, M. R., Zine-Dine, K., Bouzidi, D., Bourhnane, S., & Benhaddou, D. (2024) · International Conference on Intelligent Computing in Data Sciences (ICDS) · doi:10.1109/icds62089.2024.10756466 · Cited by 4
LoRAExit: Empowering Dynamic Modulation of LLMs in Resource-limited Settings using Low-rank Adapters
Liu, J., Tang, P., Hou, X., Li, C., & Heng, P. (2024) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2024.findings-emnlp.539 · Cited by 4
CARN: Complexity-Aware Routing Network for Efficient and Adaptive Inference
Gaire, R. R., & Roohi, A. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00314 · Cited by 4
Dataset Pruning Using Early Exit Networks
Görmez, A., & Koyuncu, E. (2026) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3785502 · Cited by 4
Context-aware adaptation of deep learning models for IoT devices
Wang, H., Xingshe, Z. H. O. U., Yu, Z., Sicong, L. I. U., Guo, B., Wu, Y., Liu, J., & Wang, H. (2020) · Scientia Sinica Informationis · doi:10.1360/ssi-2020-0067 · Cited by 4
NeuroFlux: Memory-Efficient CNN Training Using Adaptive Local Learning
Saikumar, D., & Varghese, B. (2024) · European Conference on Computer Systems · doi:10.1145/3627703.3650067 · Cited by 4
Context-Aware Collaborative Object Recognition For Distributed Multi Camera Time Series Data
Shin, P. W., Sampson, J., & Narayanan, V. (2019) · International Symposium on Information and Communication Technology · doi:10.1145/3368926.3369666 · Cited by 4
Wang, Q., Jin, G., Li, Q. '., Wang, K., Yang, Z., & Wang, H. (2021) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber53097.2021.9588142 · Cited by 4
Big–Little Adaptive Neural Networks on Low-Power Near-Subthreshold Processors
Shen, Z., Howard, N., & Nunez-Yanez, J. L. (2022) · Journal of Low Power Electronics and Applications · doi:10.3390/jlpea12020028 · Cited by 4
Increased Leverage of Transprecision Computing for Machine Vision Applications at the Edge
Minhas, U. I., Lee, J., Mukhanov, L., Karakonstantis, G., Vandierendonck, H., & Woods, R. (2022) · Journal of Signal Processing Systems · doi:10.1007/s11265-022-01784-1 · Cited by 4
ReX: An Efficient Approach to Reducing Memory Cost in Image Classification
Qian, X., Hang, R., & Liu, Q. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20106 · Cited by 4
A Dynamic and Collaborative Deep Inference Framework for Human Motion Analysis in Telemedicine
Boldo, M., Damiano Carra, B., Quaglia, D., & Bombieri, N. (2023) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge60047.2023.00043 · Cited by 4
Mobiprox: Supporting Dynamic Approximate Computing on Mobiles
Fabjančič, M., Machidon, O. M., Sharif, H., Zhao, Y., Misailovíc, S., & Pejović, V. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3365957 · Cited by 4
A Converting Autoencoder Toward Low-latency and Energy-efficient DNN Inference at the Edge
Mahmud, H., Kang, P., Desai, K., Lama, P., & Prasad, S. K. (2024) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw63119.2024.00117 · Cited by 4
IIoT Based Hierarchical Data Distribution Strategy over Edge and End Device
Yu, H., Yu, D., Hu, Y., & Wang, C. (2020) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc51575.2020.9345250 · Cited by 4
Dong, L., Zhai, Y., Wu, J., & Shen, J. (2021) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid51090.2021.00062 · Cited by 4
Recurrent Convolution for Compact and Cost-Adjustable Neural Networks: An Empirical StudyPreprint
Zhang, Z., & Jung, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.09809 · Cited by 4
An end-to-end approach for speeding up neural network inferencePreprint
Herrmann, C., Bowen, R. S., & Zabih, R. (2018) · arXiv (Cornell University) · Cited by 4
Understanding the Robustness of Multi-Exit Models under Common CorruptionsPreprint
Mehra, A., Seto, S., Jaitly, N., & Theobald, B.-J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.01562 · Cited by 4
Early-Exit Neural Networks with Nested Prediction SetsPreprint
Jazbec, M., Forré, P. D., Mandt, S., Zhang, D., & Nalisnick, E. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.05931 · Cited by 4
Taherisadr, M., & Elmalaki, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.05864 · Cited by 4
Guzmán, D. W. R. (2024) · doi:10.5463/thesis.738 · Cited by 4
Dynamic Vocabulary Pruning in Early-Exit LLMsPreprint
Vincenti, J., Sadek, K. A., Velja, J., Nulli, M., & Jazbec, M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.18952 · Cited by 4
Solanki, N., Tabrizchi, S., Sohrabi, S., Schmidt, J. M., & Roohi, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.09822 · Cited by 4
WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIPPreprint
Kimhi, M., Koifman, E., Rivlin, E., Schwartz, E., & Baskin, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.21153 · Cited by 4
Navaneet, K. L., Koohpayegani, S. A., Sleiman, E., & Pirsiavash, H. (2023) · arXiv (Cornell University) · doi:10.13016/m2peuy-x3cx · Cited by 4
Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth AnalysisPreprint
Kapl, F., Angelis, E., Höppe, T., Maile, K., von Oswald, J., Scherrer, N., & Bauer, S. (2025) · arXiv.org · doi:10.48550/arxiv.2512.08819 · Cited by 8
PARE: Pruning and Adaptive Routing for Efficient Video GenerationPreprint
Wang, Y., Wang, Y., Xue, T., Qiao, Y., Wang, Y., Chen, X., & Xu, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.27336 · Cited by 4
Hierarchical Attentive Feature Aggregation for Person Re-Identification
Dong, H., & Lu, P. (2024) · IEEE Access · doi:10.1109/access.2024.3389698 · Cited by 3
An Overview of Adaptive Dynamic Deep Neural Networks via Slimmable and Gated Architectures
Johnsen, T. K., Harshbarger, I. A., & Levorato, M. (2024) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc62082.2024.10827241 · Cited by 3
FreeNet: An efficient frequency-domain early exiting network for dynamic inference
Yan, Y., Li, X., Cui, K., Sun, H., & Yu, Z. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113155 · Cited by 3
The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute
Jin, Y., Wei, G.-Y., & Brooks, D. (2025) · arXiv · doi:10.48550/arxiv.2505.14733
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.