The DOI matches its Crossref record; 278 of the 280 references it cites were found in a registry or an index.
Dynamic Neural Networks: A Survey
Open accessAbstract
Dynamic neural network is an emerging research topic in deep learning. Compared to static models which have fixed computational graphs and parameters at the inference stage, dynamic networks can adapt their structures or parameters to different inputs, leading to notable advantages in terms of accuracy, computational efficiency, adaptiveness, etc. In this survey, we comprehensively review this rapidly developing area by dividing dynamic networks into three main categories: 1) sample-wise dynamic models that process each sample with data-dependent architectures or parameters; 2) spatial-wise dynamic networks that conduct adaptive computation with respect to different spatial locations of image data; and 3) temporal-wise dynamic models that perform adaptive inference along the temporal dimension for sequential data such as videos and texts. The important research problems of dynamic networks, e.g., architecture design, decision making scheme, optimization technique and applications, are reviewed systematically. Finally, we discuss the open problems in this field together with interesting future research directions.
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
“In contrast, DNNs enhance expressive ability by dynamically adjusting the network depth or activating certain specific modules as needed.”
From Advancements in the estimation of the state of charge of lithium-ion battery: a comprehensive review of traditional and deep learning approaches (2025) · cites this paper as [130]
In the citing paper
“DNNs[130] offer a potential solution, advancing the research of SOC estimation through their abilities to adaptively adjust their structure and parameters based on input data during the inference phase, providing greater flexibility than traditional static networks.”
From Advancements in the estimation of the state of charge of lithium-ion battery: a comprehensive review of traditional and deep learning approaches (2025) · cites this paper as [130]
In the citing paper
“DNNs, however, allocate computational resources efficiently by activating specific modules as needed.”
From Advancements in the estimation of the state of charge of lithium-ion battery: a comprehensive review of traditional and deep learning approaches (2025) · cites this paper as [130]
In the citing paper
“In contrast, static networks maintain fixed configurations post-training, which may be suboptimal in practical applications due to limited representational ability and inflexible resource allocation.”
From Advancements in the estimation of the state of charge of lithium-ion battery: a comprehensive review of traditional and deep learning approaches (2025) · cites this paper as [130]
In the citing paper
“DNNs are compatible with existing NN technologies and can seamlessly incorporate various advanced DL technologies.”
From Advancements in the estimation of the state of charge of lithium-ion battery: a comprehensive review of traditional and deep learning approaches (2025) · cites this paper as [130]
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
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
Self-citationSqueeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
CBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_1 · Cited by 25,853
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Research works printed but not linked: 7
- 10.5555/2999134.2999257 · DOI
- 10.18653/vl/n19-142 · DOI
- Ha, Hypernetworks
- Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
- Pan, VA-RED 2: Video adaptive redundancy reduction
- 10.5555/3045118.3045336 · DOI
- Gumbel, 1954, Statistical Theory of Extreme Values and Some Practical Applications(NBS Applied Mathematics Series)
Cited by
Sorted by citations
Items 901–946 of 946
Adaptive TinyML with Shift-Aware Routing for Human Activity Recognition Under Distribution Shifts
Kaya, H., & Kılıçaslan, M. (2026) · Applied Sciences · doi:10.3390/app16199711
Yu, F., Wei, Y., Zhu, L., Jiang, X., & Li, H. (2026) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001426400677
Li, J., Lin, P., Changlong, C., & Zhou, Z. (2026) · The European Physical Journal B · doi:10.1140/epjb/s10051-026-01263-7
Zhou, Z., Zhang, P., Yang, Y., Li, B., Lang, Y., & Miao, D. (2026) · Measurement · doi:10.1016/j.measurement.2026.123354
Sulaima, M. F., Arvindhan, M., Krejcar, O., & Namazi, H. (2026) · Energy Nexus · doi:10.1016/j.nexus.2026.100867
Ruda, K., & Kromkach, V. O. (2026) · Науковий вісник НЛТУ України · doi:10.36930/40360419
Dynamic Inference Techniques in Convolutional Neural Networks: A Review
Kareh, J., & Imad, R. (2026) · AI · doi:10.3390/ai7100402
Optimization of Statistical Machine Translation Method Integrating Neural Network Algorithm
Guo, S. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-95-7622-7_29
A Novel PV Power Extraction Improvement by Using Modified Osprey Optimization MPPT Methodology
Nagarani, R., Basha, C. H., & Irfan, M. M. (2026) · International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE) · doi:10.1109/aikiie69997.2026.11708037
Adaptive model inference under computational resource constraints
Yu, H. (2022) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)
Fast and flexible? Evaluating CLIP for image classification in a marketing context
Lee, Y. J., Chang, S. R., & Park, C. H. (2026) · Journal of Marketing Analytics · doi:10.1057/s41270-026-00550-7
AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens
Jajal, P., Eliopoulos, N. J., Chou, B. S.-H., Thiruvathukal, G. K., Lu, Y.-H., & Davis, J. C. (2026) · doi:10.1109/cvprf71909.2026.00255
Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs
Lin, Y., Yu, S., Yang, Y., Cheng, G., & Xiao, J. (2026) · doi:10.1109/cvprf71909.2026.00858
Wafer Map Defect Pattern Recognition via Hierarchical Slimmable Network
Le, T. D., Dinh, T. N., Choi, J., Ahn, J. S., Mondal, S., Doan, V. H. M., & Oh, J. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3742081
Multi-Exit Complexity-Aware DetNet for Massive MIMO Uplink Detection
Li, W. (2026) · International Conference on Biomedical Engineering and Bioinformatics for Health (ICBEBH) · doi:10.1109/icbebh71590.2026.11722418
Dynamic Structural-Textural Routing for Internet of Underwater Things Monitoring
Ologunmeta, A., Zhao, Y., Kannan, S., & Fough, N. (2026) · ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)
From Columns to Blocks: Expansion Geometries for Continual LearningPreprint
Kumar, N., & Srivastava, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7593348
Amiri, M., Mokari, A., & Bocklitz, T. W. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02369-8
Dynamic Model Switching for Vision-Based Inspection in UAV Applications
Chirravuri, G. T., Battseren, B., & Hardt, W. (2026) · International Symposium on Computer Science and Educational Technology (ISCSET) · doi:10.1109/iscset70652.2026.11722958
RAYHAN, M. A. S., Hiya, H., & Dhar, A. S. (2026) · Research Square · doi:10.21203/rs.3.rs-11335280/v1
WADNet: Weather Adversarial Decoupling Network for Marine Ship Instance Segmentation
Sun, Y., Zhang, L., Zhu, Z., & Yuan, S. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14201906
Hearing's Blind Spots: Toward Perceptual Compute Allocation in Neural Text-to-SpeechPreprint
Gupta, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.14056
Kumar, N., & Srivastava, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7615680
Adaptive Deep Learning for Vision and Multimodal Understanding with Heterogeneous Data
Liang, Y. (2026) · eScholarship (California Digital Library)
IntelliLayer: A Deep Learning Architecture for Dynamic Decision Intelligence
Mounika, G., Shwetha, V., & Sridhar, D. K. (2026) · JEE · doi:10.65713/jeev2i401
ACME: Aspect-aware Causal Mixture-of-Experts model for Multimodal Sentiment Analysis
Mengxiao, Z., Zhang, S., Zhang, J., Zhu, G., Zhang, S., & Chen, M. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729941
Ruda, K., & Kromkach, V. O. (2026) · Cybersecurity Education Science Technique · doi:10.28925/2663-4023.2026.34.1340
(2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728886
Lee, H., & Lim, J.-H. (2026) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2026.3745448
Computer-aided triage and diagnostic routing for efficient medical image classification
Pan, W., Wang, S., Ma, Z., Lv, C., & Wang, Y. (2026) · Discover Computing · doi:10.1007/s10791-026-10695-9
Self-citationLi, C., Tang, Y., Duan, X., & Zhong, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7669854
Uncertainty-Guided Selective Temporal Refinement for mmWave Radar Human–Background Recognition
Meng, E., Miao, Z., Pu, S., Ai, L., & Shi, S. (2026) · Electronics · doi:10.3390/electronics15214980
Sembiring, M. A. (2026) · Journal of Applied Data Sciences · doi:10.47738/jads.v7i4.1459
Dynamic content-aware modulation network for efficient single-image super-resolution
Li, Y., Wu, F., & Ye, W. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116750
Efficient Neural Network Inference on CPU-Centered Edge Device
Zhang, G. L. (2026) · IFIP/IEEE International Conference on Very Large Scale Integration · doi:10.1109/vlsi-soc70418.2026.11740619
Memoona, Hashir, M. H., & Kim, S. W. (2026) · PLoS ONE · doi:10.1371/journal.pone.0359774
Huang, Y., Zhang, X., Qian, J., & Chen, G. (2026) · doi:10.1109/aice71085.2026.11736924
Klein, Z., & Price, V. (2026) · International Journal of Advanced Engineering and Technology Research · doi:10.54097/jc1bep53
Boya, B. F. B. A., Kengne, J., Nanfak, A., Zourmba, K., Telem, A. N. K., Nkapkop, J. D. D., & Effa, J. Y. (2026) · AEU - International Journal of Electronics and Communications · doi:10.1016/j.aeue.2026.156702
Anytime-Budget Embedding Allocation for DLRMs via Continuous-Capacity Multiple-Choice Knapsack
Guo, C., Xue, R., & Zhang, J. J. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840937
Becerra, C. R. D., & Cuevas, F. J. (2026) · Journal of Imaging · doi:10.3390/jimaging12110548
Dynamic Neuron Mechanisms for Deep Learning Adaptability Benchmark Analysis
Sembiring, M. A., Efendi, S., Budiman, M. A., & Harumy, T. H. F. (2026) · International Conference on Creative Communication and Innovative Technology (ICCIT) · doi:10.1109/iccit70127.2026.11749257
Gunda, S. K., Ganashree, R., Prasanth, P. S., & Mogare, S. B. (2026) · doi:10.1109/icact70625.2026.11748799
Margin-Guided Adaptive Model Routing for Resource-Efficient Speaker Verification on Edge Devices
Nurimov, P., & Mamatov, N. (2026) · Computation · doi:10.3390/computation14110271
Ravikumar, S. (2026) · International Journal of Computer Networks And Applications · doi:10.22247/ijcna/2026/51
QNRs: toward language for intelligent machines
Drexler, E. (2021) · Oxford University Research Archive (ORA) (University of Oxford)
Metadata
- Authors
- Han, Y., Huang, G., Song, S., Yang, L., Wang, H., & Wang, Y.
- Affiliations
- Tsinghua University (CN)
- Beijing Academy of Artificial Intelligence (CN)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2022-11-01
- Volume
- 44
- Issue
- 11
- Pages
- 7436-7456
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W3204647170
- Cited by
- 848
- References
- 280
- Citations by year
- 2026: 162 · 2025: 213 · 2024: 191 · 2023: 170 · 2022: 74
- FWCI
- 7.34
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science and Technology Major Project (2018AAA0100701)
- National Natural Science Foundation of China (61906106, 62022048)
- Tsinghua University
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- dynamic neural networks, adaptive computation, adaptive inference, architectural design, decision-making scheme, optimization methods, sequential data, video analysis, text analysis
- MeSH terms
- Algorithms, Neural Networks, Computer
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
