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 301–400 of 1,000
MDINFERENCE: Balancing Inference Accuracy and Latency for Mobile Applications
Ogden, S. S., & Guo, T. (2020) · IEEE International Conference on Cloud Engineering · doi:10.1109/ic2e48712.2020.00010 · Cited by 32
Safety-Assured Design and Adaptation of Learning-Enabled Autonomous Systems
Zhu, Q., Huang, C., Jiao, R., Lan, S., Liang, H., Liu, X., Wang, Y., Wang, Z., & Xu, S. (2021) · Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.1145/3394885.3431623 · Cited by 33
Resource-Constrained Edge AI with Early Exit Prediction
Dong, R., Mao, Y., & Zhang, J. (2022) · Journal of Communications and Information Networks · doi:10.23919/jcin.2022.9815196 · Cited by 32
DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks
Chen, S., Haque, M., Liu, C., & Yang, W. M. (2022) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3551349.3561158 · Cited by 32
Fresa, A., & Champati, J. P. (2023) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2023.3267458 · Cited by 32
AdaDiff: Accelerating Diffusion Models Through Step-Wise Adaptive Computation
Tang, S., Wang, Y., Ding, C., Liang, Y., Li, Y., & Xu, D. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72986-7_5 · Cited by 32
High Frequency Residual Learning for Multi-Scale Image ClassificationPreprint
Cheng, B., Xiao, R., Wang, J., Huang, T. S., & Zhang, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.02649 · Cited by 32
Speculative Decoding and Beyond: An In-Depth Survey of TechniquesPreprint
Hu, Y., Liu, Z., Dong, Z., Peng, T., McDanel, B., & Zhang, S. Q. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.19732 · Cited by 32
Self-citationEncode, Think, Decode: Scaling test-time reasoning with recursive latent thoughtsPreprint
Koishekenov, Y., Lipani, A., & Cancedda, N. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.07358 · Cited by 32
Conditional computation in neural networks: Principles and research trends
Scardapane, S., Baiocchi, A., Devoto, A., Marsocci, V., Minervini, P., & Pomponi, J. (2024) · Intelligenza Artificiale · doi:10.3233/ia-240035 · Cited by 31
MobiVQA: Efficient On-Device Visual Question Answering
Cao, Q., Khanna, P., Lane, N. D., & Balasubramanian, A. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3534619 · Cited by 31
DCNNet: A Distributed Convolutional Neural Network for Remote Sensing Image Classification
Zhang, T., Wang, Z., Cheng, P., Xu, G., & Sun, X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3243238 · Cited by 31
Dong, C., Shafiq, M., Dabel, M. M. A., Sun, Y., & Tian, Z. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3339468 · Cited by 31
A collaborative cloud-edge computing framework in distributed neural network
Xu, S., Zhang, Z., Kadoch, M., & Cheriet, M. (2020) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-020-01794-2 · Cited by 31
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate HallucinationsPreprint
Gema, A. P., Chen, J., Abdulaal, A., Diethe, T., Teare, P., Alex, B., Minervini, P., & Saseendran, A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.18860 · Cited by 31
Anytime Recognition with Routing Convolutional Networks
Jie, Z., Sun, P., Li, X. S., Feng, J., & Liu, W. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2959322 · Cited by 30
Enomoro, S., & Eda, T. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i8.16900 · Cited by 30
Harmonized Dense Knowledge Distillation Training for Multi-Exit Architectures
Wang, X., & Li, Y. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i11.17225 · Cited by 30
Early-exit deep neural networks for distorted images: providing an efficient edge offloading
Pacheco, R. G., Oliveira, F. D. V. R., & Couto, R. S. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685469 · Cited by 30
Towards Edge Computing Using Early-Exit Convolutional Neural Networks
Pacheco, R. G., Bochie, K., Gilbert, M. S., Couto, R. S., & Campista, M. E. M. (2021) · Information · doi:10.3390/info12100431 · Cited by 30
Content-Aware Adaptive Device–Cloud Collaborative Inference for Object Detection
Hu, Y., Li, Z., Chen, Y., Cheng, Y., Cao, Z., & Liu, J. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3279579 · Cited by 30
ClassyNet: Class-Aware Early-Exit Neural Networks for Edge Devices
Ayyat, M., Nadeem, T., & Krawczyk, B. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3344120 · Cited by 30
Neural network developments: A detailed survey from static to dynamic models
Verma, P. R., Singh, N. P., Pantola, D., & Cheng, X. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109710 · Cited by 32
Kuen, J., Kong, X., Lin, Z., Wang, G., Yin, J., See, S. C. W., & Tan, Y. (2018) · 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.2018.00827 · Cited by 30
Complexity-aware Adaptive Training and Inference for Edge-Cloud Distributed AI Systems
Long, Y., Chakraborty, I., Srinivasan, G., & Roy, K. (2021) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs51616.2021.00061 · Cited by 30
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
Chuang, Y.-S., Xie, Y., Luo, H., Kim, Y., Glass, J., & He, P. (2023) · arXiv · doi:10.48550/arxiv.2309.03883 · Cited by 29
“The idea of applying language heads directly to the hidden states of the middle layers, known as early exit (Teerapittayanon et al., 2016; Elbayad et al., 2020; Schuster et al., 2022), has proven to be effective even without special training process (Kao et al., 2020), as the residual connections…”
BackgroundYou, H., Barnes, C., Zhou, Y., Kang, Y., Du, Z., Zhou, W., Zhang, L., Nitzan, Y., Liu, X., Lin, Z., et al. (2025) · 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/cvpr52734.2025.01684 · Cited by 29
Carnero, A., Martín, C., Torres, D. R., Garrido, D., Díáz, M., & Rubio, B. (2021) · IEEE Access · doi:10.1109/access.2021.3110291 · Cited by 29
Wang, P., Ouyang, T., Liao, G., Gong, J., Yu, S., & Chen, X. (2022) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2022.102664 · Cited by 29
Sun, Z., Du, X., Song, F., Wang, S., & Li, L. (2024) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3597503.3639120 · Cited by 29
Differentiable Branching In Deep Networks for Fast Inference
Scardapane, S., Comminiello, D., Scarpiniti, M., Baccarelli, E., & Uncini, A. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054209 · Cited by 29
FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear ApproximationPreprint
Liu, D., Yu, Y., Zhang, J., Li, Y., Lengerich, B. J., & Wu, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.20353 · Cited by 29
Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving
Dai, Y., Pan, R., Iyer, A. P., Li, K., & Netravali, R. (2024) · ACM SIGOPS Symposium on Operating Systems Principles (SOSP) · doi:10.1145/3694715.3695963 · Cited by 28
An Energy-Efficient Intrusion Detection Offloading Based on DNN for Edge Computing
Simioni, J. A., Viegas, E. K., Santin, A. O., & de Matos, É. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3544060 · Cited by 28
Hoseinnia, F., Ghatee, M., & Chehreghani, M. H. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113615 · Cited by 28
Xu, X., Chen, H., Lyu, M., Zhao, S., Xiong, Y., Lin, Z., Han, J., & Ding, G. (2025) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2025.naacl-long.75 · Cited by 28
TinyTTA: Efficient Test-time Adaptation via Early-exit Ensembles on Edge Devices
Jia, H., Kwon, Y. D., Orsino, A., Dang, T., Talia, D., & Mascolo, C. (2024) · neural information processing systems · doi:10.52202/079017-1371 · Cited by 28
Leaky Gated Cross-Attention for Weakly Supervised Multi-Modal Temporal Action Localization
Lee, J.-T., Yun, S., & Jain, M. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00089 · Cited by 28
Two-stage Human Activity Recognition on Microcontrollers with Decision Trees and CNNs
Daghero, F., Pagliari, D. J., & Poncino, M. (2022) · Conference on Ph.D. Research in Microelectronics and Electronics · doi:10.1109/prime55000.2022.9816745 · Cited by 28
Dong, P., Wu, Q., Zhang, X., & Ding, G. (2022) · China Communications · doi:10.23919/jcc.2022.08.001 · Cited by 28
Jiang, S., Shuai, X., & Xing, G. (2024) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn61024.2024.00007 · Cited by 28
Class-specific early exit design methodology for convolutional neural networks
Bonato, V., & Bouganis, C.-S. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107316 · Cited by 28
Shi, L., Xu, Z., Sun, Y., Shi, Y., Fan, Y., & Ding, X. (2021) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-021-01223-1 · Cited by 28
Cost-Aware Contrastive Routing for LLMs
Shirkavand, R., Gao, S., Yu, P., & Huang, H. (2025) · neural information processing systems · doi:10.52202/085713-5202 · Cited by 27
Cross-layer Attention Sharing for Pre-trained Large Language Models
Mu, Y., Wu, Y., Fan, Y., Wang, C. Q., Li, H., Zeng, J., He, Q., Yang, M., Meng, F., Zhou, J., et al. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.616 · Cited by 28
Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach
Tang, C., Zhai, H., Ouyang, K., Wang, Z., Zhu, Y., & Zhu, W. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548001 · Cited by 27
E2CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning
Görmez, A., Dasari, V. R., & Koyuncu, E. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9891952 · Cited by 27
Gao, X., Zhu, W., Gao, J., & Yin, C. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095864 · Cited by 27
Systematic Literature Review on Cost-Efficient Deep Learning
Klemetti, A., Raatikainen, M., Myllyaho, L., Mikkonen, T., & Nurminen, J. K. (2023) · IEEE Access · doi:10.1109/access.2023.3275431 · Cited by 27
Boosted Dynamic Neural Networks
Yu, H., Li, H., Hua, G., Huang, G. M., & Shi, H. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i9.26302 · Cited by 27
Self-Contrastive Learning: Single-Viewed Supervised Contrastive Framework Using Sub-network
Bae, S., Kim, S., Ko, J., Lee, G., Noh, S., & Yun, S.-Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25091 · Cited by 27
Map-and-Conquer: Energy-Efficient Mapping of Dynamic Neural Nets onto Heterogeneous MPSoCs
Bouzidi, H., Odema, M., Ouarnoughi, H., Niar, S., & Faruque, M. A. A. (2023) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac56929.2023.10247722 · Cited by 27
Toward Fairness Through Fair Multi-Exit Framework for Dermatological Disease Diagnosis
Chiu, C.-H., Chung, H.-W., Chen, Y.-J., Shi, Y., & Ho, T.-Y. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43898-1_10 · Cited by 27
SplitEE: Early Exit in Deep Neural Networks with Split Computing
Bajpai, D. J., Trivedi, V., Yadav, S. L., & Hanawal, M. K. (2023) · International Conference on AI-ML Systems (AIMLSystems) · doi:10.1145/3639856.3639873 · Cited by 27
Convolutional Networks with Adaptive Computation Graphs.Preprint
Veit, A., & Belongie, S. (2017) · arXiv (Cornell University) · Cited by 27
Efficiently Controlling Multiple Risks with Pareto TestingPreprint
Laufer-Goldshtein, B., Fisch, A., Barzilay, R., & Jaakkola, T. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.07913 · Cited by 27
FBS: Modeling Native Parallel Reading inside a TransformerPreprint
Wang, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.21708 · Cited by 27
Online deep learning’s role in conquering the challenges of streaming data: a survey
Sulaiman, M. A., Farmanbar, M., Kagami, S., Belbachir, A. N., & Rong, C. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02351-3 · Cited by 26
E4: Energy-Efficient DNN Inference for Edge Video Analytics via Early Exiting and DVFS
Zhang, Z., Zhao, Y., Chang, M., Lin, C., & Liu, J. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i1.32104 · Cited by 25
Lee, C.-S., Hong, S., Hong, S.-B., & Kim, T. (2020) · ETRI Journal · doi:10.4218/etrij.2020-0112 · Cited by 26
Learning Early Exit for Deep Neural Network Inference on Mobile Devices through Multi-Armed Bandits
Ju, W., Bao, W., Yuan, D., Ge, L., & Zhou, B. (2021) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid51090.2021.00011 · Cited by 26
Semi-HFL: semi-supervised federated learning for heterogeneous devices
Zhong, Z., Wang, J., Bao, W., Zhou, J., Zhu, X., & Zhang, X. (2022) · Complex & Intelligent Systems · doi:10.1007/s40747-022-00894-4 · Cited by 26
Zhu, W., Wang, P., Ni, Y., Xie, G., & Wang, X. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-industry.48 · Cited by 26
Learning to optimize: A tutorial for continuous and mixed-integer optimization
Chen, X., Liu, J., & Yin, W. (2024) · Science China Mathematics · doi:10.1007/s11425-023-2293-3 · Cited by 26
Dynamic Workload Allocation for Edge Computing
Hung, Y.-W., Chen, Y., Lo, C., So, A. G., & Chang, S.-C. (2021) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2021.3049520 · Cited by 26
VA-RED$^2$: Video Adaptive Redundancy ReductionPreprint
Pan, B., Panda, R., Fosco, C. L., Lin, C.-C., Andonian, A., Meng, Y., Saenko, K., Oliva, A., & Feris, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.07887 · Cited by 26
BAGEN: Are LLM Agents Budget-Aware?Preprint
Lin, Y., Wang, Z., Liu, M., Shan, Y., Bai, L., Zhang, J., Jin, X., Chen, B., Su, J., Wang, X., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.00198 · Cited by 26
Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks
Wang, Z., Fang, Y., Cao, J., Ren, H., & Xu, R. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i2.32150 · Cited by 25
Dong, J., Jiang, J., Jiang, K., Li, J., & Zhang, Y. (2025) · 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/cvpr52734.2025.02870 · Cited by 26
Selected Aspects of Non orthogonal Multiple Access for Future Wireless Communications
Flizikowski, A., Marciniak, T., Wysocki, T. A., & Oyerinde, O. O. (2023) · Mathematics in Computer Science · doi:10.1007/s11786-023-00561-y · Cited by 25
Towards Inference Efficient Deep Ensemble Learning
Li, Z., Ren, K., Yang, Y., Jiang, X., Yang, Y., & Li, D. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i7.26048 · Cited by 25
Dynamic Voting for Efficient Reasoning in Large Language Models
Xue, M., Liu, D., Lei, W., Ren, X., Yang, B., Xie, J., Zhang, Y., Peng, D., & Lv, J. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.203 · Cited by 25
Fu, Y., Yang, H., Yuan, J., Li, M., Wan, C., Krishnamoorthi, R., Chandra, V., & Lin, Y. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.00843 · Cited by 25
Anytime Dense Prediction with Confidence AdaptivityPreprint
Liu, Z., Xu, Z., Wang, H.-J., Darrell, T., & Shelhamer, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00749 · Cited by 25
Ullah, S. A., Hassan, S. A., Abou-Zeid, H., Qureshi, H. K., Jung, H., Mahmood, A., Gidlund, M., Imran, M. A., & Hossain, E. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3576571 · Cited by 24
Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation
Wang, Y., Ren, R., Wang, Y., Zhao, W. X., Liu, J., Wu, H., & Wang, H. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730112 · Cited by 25
Hardware design and the competency awareness of a neural network
Ding, Y., Jiang, W., Lou, Q., Liu, J., Xiong, J., Hu, X. S., Xu, X., & Shi, Y. (2020) · Nature Electronics · doi:10.1038/s41928-020-00476-7 · Cited by 24
Yang, L., Shen, X., Zhong, C., & Liao, Y. (2022) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2022.09.005 · Cited by 24
OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses
Shrestha, R., Kafle, K., & Kanan, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20044-1_40 · Cited by 24
Pacheco, R. G., Couto, R. S., & Simeone, O. (2023) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2023.103679 · Cited by 24
In-Situ Model Downloading to Realize Versatile Edge AI in 6G Mobile Networks
Huang, K., Hai, W., Liu, Z., & Qi, X. (2023) · IEEE Wireless Communications · doi:10.1109/mwc.010.2200546 · Cited by 24
Xia, G., & Bouganis, C.-S. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01593 · Cited by 24
Adapting Neural Networks at Runtime: Current Trends in At-Runtime Optimizations for Deep Learning
Sponner, M., Waschneck, B., & Kumar, A. S. (2024) · ACM Computing Surveys · doi:10.1145/3657283 · Cited by 24
Approximate LSTMs for Time-Constrained Inference: Enabling Fast Reaction in Self-Driving Cars
Kouris, A., Venieris, S. I., Rizakis, M., & Bouganis, C.-S. (2020) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2020.2969195 · Cited by 24
Elbert: Fast Albert with Confidence-Window Based Early Exit
Xie, K., Lu, S., Wang, M., & Wang, Z. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414572 · Cited by 24
Deep Learning Video Analytics on Edge Computing Devices
Tan, T., & Cao, G. (2021) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/secon52354.2021.9491614 · Cited by 24
Project CLAI: Instrumenting the Command Line as a New Environment for AI AgentsPreprint
Agarwal, M., Barroso, J. J., Chakraborti, T., Dow, E. M., Fadnis, K., Godoy, B., Pallan, M., & Talamadupula, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.00762 · Cited by 24
PAC Confidence Predictions for Deep Neural Network ClassifiersPreprint
Park, S., Li, S., Lee, I., & Bastani, O. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.00716 · Cited by 24
Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMsPreprint
Li, Z., Li, Y., & Zhou, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.07996 · Cited by 27
SatCooper: Enhancing Cooperative Inference Analytics for Satellite Service via Multi-Exit DNNs
Zhang, Q., Wang, S., Guan, J., Donta, P. K., Ma, X., Prasad, R. R. V., Dustdar, S., & Liu, X. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3556457 · Cited by 24
MIA-Former: Efficient and Robust Vision Transformers via Multi-Grained Input-Adaptation
Yu, Z., Fu, Y., Li, S., Li, C., & Lin, Y. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20879 · Cited by 23
Smartadapt: Multi-branch Object Detection Framework for Videos on Mobiles
Xu, R., Mu, F., Lee, J., Mukherjee, P., Chaterji, S., Bagchi, S., & Li, Y. (2022) · 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/cvpr52688.2022.00256 · Cited by 23
Pruning and Early-Exit Co-Optimization for CNN Acceleration on FPGAs
Korol, G., Jordan, M. G., Rutzig, M. B., Castrillón, J., & Beck, A. C. S. (2023) · Design, Automation, and Test in Europe · doi:10.23919/date56975.2023.10137244 · Cited by 23
The Case for Hierarchical Deep Learning Inference at the Network Edge
Al-Atat, G., Fresa, A., Behera, A. P., Moothedath, V. N., Gross, J., & Champati, J. P. (2023) · doi:10.1145/3597062.3597278 · Cited by 23
EDANAS: Adaptive Neural Architecture Search for Early Exit Neural Networks
Gambella, M., & Roveri, M. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191876 · Cited by 23
LECO: Improving Early Exiting via Learned Exits and Comparison-based Exiting Mechanism
Zhang, J., Tan, M., Dai, P., & Zhu, W. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-srw.43 · Cited by 23
BOSE: Block-Wise Federated Learning in Heterogeneous Edge Computing
Wang, L., Xu, Y., Xu, H., Jiang, Z., Chen, M., Zhang, W., & Qian, C. (2023) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2023.3316421 · Cited by 23
Zhang, Z., Zhao, Y., & Liu, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-48424-7_18 · Cited by 24
Optimizing Retrieval-augmented Reader Models via Token Elimination
Berchansky, M., Izsak, P., Caciularu, A., Dagan, I., & Wasserblat, M. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.93 · Cited by 23
Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Client
Xia, J., Zhang, Y., & Shi, Y. (2024) · doi:10.1145/3676536.3676815 · Cited by 23
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.