Model Compression and Acceleration for Deep Neural Networks: The Principles, Progress, and Challenges
The DOI matches its Crossref record; 61 of the 67 references it cites were found in a registry or an index.
Abstract
In recent years, deep neural networks (DNNs) have received increased attention, have been applied to different applications, and achieved dramatic accuracy improvements in many tasks. These works rely on deep networks with millions or even billions of parameters, and the availability of graphics processing units (GPUs) with very high computation capability plays a key role in their success. For example, Krizhevsky et al. achieved breakthrough results in the 2012 ImageNet Challenge using a network containing 60 million parameters with five convolutional layers and three fully connected layers. Usually, it takes two to three days to train the whole model on the ImagetNet data set with an NVIDIA K40 machine. In another example, the top face-verification results from the Labeled Faces in the Wild (LFW) data set were obtained with networks containing hundreds of millions of parameters, using a mix of convolutional, locally connected, and fully connected layers. It is also very time-consuming to train such a model to obtain a reasonable performance. In architectures that only rely on fully connected layers, the number of parameters can grow to billions.
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
“but there is no review discussing all three categories which in future will be integrated seamlessly to design effective and efficient DNNs in the new edge intelligence era.”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [26]
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 · cited 1×
“Recently, more state-of-the-art architectures are used as baseline models in many works, including network in networks [67], VGGNets [68], and ResNets [69].”
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 · cited 4×
“[1] achieved breakthrough results in the 2012 ImageNet Challenge using a network containing 60 million parameters with five convolutional layers and three fully-connected layers.”
MethodInfluentialGradient-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 · cited 2×
“Other popular standard models include LeNets [66], All-CNN-nets [67] and many others.”
MethodDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 1×
“The work in [51] introduced a KD compression framework, which eased the training of deep networks by following a student-teacher paradigm, in which the student was penalized according to a softened version of the teacher’s output.”
BackgroundDeepFace: Closing the Gap to Human-Level Performance in Face Verification
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.220 · Cited by 6,542 · cited 1×
“example is the top face verification results on the Labeled Faces in the Wild (LFW) dataset were obtained with networks containing hundreds of millions of parameters, using a mix of convolutional, locally-connected, and fully-connected layers [2], [3].”
MethodHan, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
Large Scale Distributed Deep Networks
Dean, J. B., Corrado, G. S., Monga, R., Chen, K., Devin, M., Mao, M., Ranzato, M., Senior, A., Tucker, P. A., Yang, K., et al. (2012) · neural information processing systems · Cited by 4,489
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408 · cited 2×
“works that directly train CNNs with binary weights, for instance, BinaryConnect [13], BinaryNet [14] and XNORNetworks [15].”
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447 · cited 2×
“Other popular standard models include LeNets [66], All-CNN-nets [67] and many others.”
Method
Cited by
Items 701–800 of 818
A Review of Optimization Techniques for Large Language Model Inference
Cao, Y., Tao, X., Cao, W., Xu, C., & Ming, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3061-8_27
BOAT: Binary Optimizer with Adaptive Thresholds
Gu, S., Zhang, G., Jia, C., & Wu, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4094-5_7
Optimized Domain-Specific Text Processing with Keyword Knowledge Distillation (KKD)
Biswas, M., Singhal, A., & Anish, P. R. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227844 · Cited by 1
Explainability-Preserving Compression: Algorithmic Design for Responsible Lightweight AI
Alang, K. S., Devaraju, P., Tuniki, R. R., Tiwari, A., & Sharma, P. (2025) · World Conference on Communication & Computing (WCONF) · doi:10.1109/wconf64849.2025.11233609
Wu, X., Li, W., Chen, Q., & Liu, X. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114319
A Lightweighted Deep Q-Network Algorithm for UAV Path Planning
Bao, Z.-H., Lin, J., & Wu, H. (2025) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2025.11.484
Block Term Decomposition of Deep Neural Networks by Variational Bayesian
Liu, J., Yang, F., Shi, C., Wu, C., & Liu, W. (2025) · Journal of Shanghai Jiaotong University (Science) · doi:10.1007/s12204-025-2873-x
Analyzing Deep Learning in Quick, Draw!: A Case Study on Hand-drawn Sketch Recognition
Alden, B., Thung, N. T., Edbert, I. S., & Aulia, A. (2025) · International Conference on Information Technology and Computing (ICITCOM) · doi:10.1109/icitcom66635.2025.11265600
Artificial Intelligence approaches for Energy Efficiency in RDF Storage – A Literature Review
Kaysouni, W. E., Rabhi, A., & Badir, H. (2025) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs66544.2025.11270584
“In parallel, general advances in deep learning model compression techniques such as pruning, quantization and Huffman coding have demonstrated substantial reductions in model size (up to 49×) and improvements in inference energy efficiency (typically 3× to 7×) [15].”
Dynamic Source-Aware Transfer Learning for Vehicular Platoon Predictive Control
Wu, Y., Zuo, Z., Wang, Y., He, D., Li, J., Zhou, Q., & Xu, H. (2025) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2025.3639826 · Cited by 1
“These techniques aim to maintain the performance of data-driven models within an acceptable accuracy range while substantially reducing parameter counts and computational complexity [21].”
Liu, X. (2025) · Journal of Computational Methods in Sciences and Engineering · doi:10.1177/14727978251380803
RetractedKartashov, I., Pushkareva, M. M., & Karandashev, Y. (2025) · Studies in computational intelligence · doi:10.1007/978-3-032-07690-8_16
Kerdpramote, P., Poomdeesittinon, A., Jamsri, R., Krueyos, P., Muangkan, R., Kulworatit, C., & Udomchaiporn, A. (2025) · International Computer Science and Engineering Conference · doi:10.1109/icsec67360.2025.11298074
Intelligence-enabled IoT with Gen AI, Powered by Model Compression and Optimization
Ukil, A., & Jara, A. J. (2025) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3714394.3750571
Autoencoder-driven MIMO architecture for underwater optical wireless communications systems
Shalol, H. M., Hassib, M. D., & Asadi, A. Z. R. A. (2025) · Journal of Optical Communications · doi:10.1515/joc-2025-0399
“In particular, traditional deep learning approaches such as weight pruning, low-bit quantization, and knowledge distillation will allow the model to be parameterized with fewer weights and have lower inference times [38, 39].”
MADTP++: Bridge the Gap Between Token and Weight Pruning for Accelerating VLTs
Cao, J., Yu, C., Ye, H., & Chen, T. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3650545 · Cited by 4
Ouyang, T., Zhao, H., Feng, H., Xu, M., Liu, J., & Song, Z. (2026) · Energy · doi:10.1016/j.energy.2026.139962
PPP: Performance Preserving Pruning for Deep Neural Networks
KAMMA, K., & Wada, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-14492-8_5
Fan, Z., Wang, Z., Li, W., Zhu, G., & Zhuang, J. (2025) · Wiley eBooks · doi:10.1002/9781394318520.refs
FM-GCN: Spatio-Temporal Graph Neural Network for Gender Recognition Using Facial Micro-Expressions
Wang, M., Xiong, Y., & Wang, M. (2026) · IEEE Access · doi:10.1109/access.2026.3656413
“Moreover, in line with recent advances in efficient deep learning summarized by reference [45], the model architecture holds potential for further optimization through state-of-the-art model compression techniques—such as parameter pruning and quantization—without significant degradation in…”
HA-OGQ: Compressing Autonomous Driving Models by Hessian-Aware Outlier Gating Quantization
Shen, Y., Zhu, H., Kuang, X., Chen, Z., Zhang, Y., & Jiang, C. (2025) · IEEE International Conference on Frontiers Technology of Information and Computer (ICFTIC) · doi:10.1109/icftic68075.2025.11324815
A Rapid Public Abnormal Event Detection System Based on the YOLOv5n Algorith
Lan, Y., & Han, H. (2025) · International Conference on Electronic Information Engineering and Computer Technology (EIECT) · doi:10.1109/eiect68017.2025.11331960
Integrating Knowledge Distillation Methods: A Sequential Multi-Stage Framework
Tian, Y., Huang, C., Tang, K., & Yao, X. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-31236-5_67
Beacon: Post-Training Quantization With Integrated Grid Selection
Zhang, S., & Saab, R. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3657704
“Quantization [1], [2], [3] has emerged as a mainstream compression technique [4], [5], [6] for deploying LLMs on resource-constrained devices and in other resource-constrained settings.”
A dimensional structure based knowledge distillation method for cross-modal learning
Si, L., Dong, H., Yang, F., HUANG, S., Yu, J., & Sun, F. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.108672 · Cited by 2
Kumar, A., Singh, K., & Ahuja, S. (2025) · International Conference on Internet of Everything, Microwave Engineering, Communication and Networks (IEMECON) · doi:10.1109/iemecon69302.2025.11365880
Credit Card Fraud Detection using Machine Learning Algorithms
Mamta Indrasing Girase, J. S. P. (2026) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-31201
Performance and Cost Optimization of Federated LLM Agents in Edge Computing Environments
Tadi, G., & Mittal, A. (2025) · International Conference on Foundation and Large Language Models (FLLM) · doi:10.1109/fllm67465.2025.11391052 · Cited by 1
Fei, Y., Zhong, Y., Wang, J., Shita, H., & Wang, X. (2026) · IEEE Access · doi:10.1109/access.2026.3665511
“These techniques include pruning [11], quantization [12], low-rank approximation [13], knowledge distillation [14], and neural architecture search [15], [16], [17], [18], [19].”
Li, X., Liu, Y., Zhang, X., Wu, G., & Fang, Y. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106004
Yu, H., Xie, H., Huang, Q., Jiang, Z., Pan, D., & Gui, W. (2026) · Journal of Analytical Atomic Spectrometry · doi:10.1039/d6ja00040a
Xu, W., Wang, J., Wang, R., Li, X., Zhang, Y., Wu, X., Li, W. D., & Qu, F. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133191 · Cited by 1
Efficient Deep Learning for Biometrics: Overview, Challenges and Trends in Ear of Frugal AI
Haroun, K., Zitouni, A., Zenakhri, A., Guessoum, M. A., & Boubchir, L. (2025) · International Conference on Software Defined Systems (SDS) · doi:10.1109/sds68531.2025.11409869 · Cited by 1
Chary, P. S., Kumar, P. T. V. R., & Ganapathy, N. (2026) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets67989.2026.11418138
A Plug-and-Play Optimization Framework via Deep-Broad Learning Cascade (DBLS)
Wang, X., Hou, X., Zeng, Y., & Zhou, X. (2025) · Asia Conference on Machine Learning and Computing (ACMLC) · doi:10.1145/3772673.3772687
Chen, C., Liu, Y., Xiong, F. B., & Zhang, F. (2025) · IEEE International Conference on Artificial Intelligence, Computer Science and Information Processing (AICSIP) · doi:10.1109/aicsip65423.2025.11427308
Bharti, A., Agrawal, A., Awotunde, J. B., & Tiwari, S. (2025) · International Conference on Emerging Technologies and Innovation for Sustainability (EmergIN) · doi:10.1109/emergin67762.2025.11450604
Novel Hybrid Compression Techniques for Full-Stack AI Deployment
Ahmed, I., Nazim, M., Mishra, V. A., Anjum, S., Kumari, P., & Taneja, N. (2025) · International Conference on Emerging Technologies and Innovation for Sustainability (EmergIN) · doi:10.1109/emergin67762.2025.11450602
AdaBit-TasNet: Speech Separation with Inference Adaptable Precision
Elminshawi, M., Chetupalli, S. R., & Habets, E. A. P. (2025) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru65441.2025.11434690
“Network pruning is a widely used compression technique to reduce the computational and memory demands of DNNs by eliminating less significant parameters [8]–[11].”
Dave, P., Dasgupta, S., Badal, K., Yuan, X., & Roy, K. (2025) · International Conference on Machine Learning and Applications · doi:10.1109/icmla66185.2025.00230
Carbon-Neutral Foundation Models Through Adaptive Transform Compression
Maggu, J. (2026) · 2026 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) · doi:10.1109/iatmsi68868.2026.11465411
“Cheng et al. [20] investigated model compression using transform quantization, whereas spatial transformer networks were introduced for the efficient execution of geometric transformations.”
Teng, S., Chen, L., Stojmenović, M., & Ma, C. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-8402-4_31
Adaptive Prototype Learning for Few-Shot Hyperspectral Image ClassificationPreprint
Shang, R., Liu, Y. 刘., Ding, J., Li, Y., Feng, J., & Xu, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6556615
Practical Considerations for Deploying Frugal AI in the IoT-Edge-Cloud Continuum
Wasielewska-Michniewska, K., Hołda, P., Paprzycki, M., Ganzha, M., Lacalle, I., & García, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-23241-0_21
4LM: Local Lightweight LLMs for Image Captioning on Embedded Systems
Bougacha, I., Hakmouni, M., Abdelhedi, M. Y., Karaa, M., Hammami, S., Alimi, A. M., & Sboui, L. (2025) · IEEE International Multi-Conference on Smart Systems & Green Process (IMC-SSGP) · doi:10.1109/imc-ssgp67001.2025.11473981
AI-Enabled RF Sensing: A Pipeline-Centric Review from Design to Recognition
Zhang, Z., Liao, X., & Hu, Z. (2026) · AI Sensors · doi:10.3390/aisens2020004
“However, in deployment, a smaller model does not automatically translate into lower end-to-end latency or energy consumption on the target device; the gain should be measured throughout the pipeline, rather than inferred from parameter counts alone [150,155].”
Jin, B., Li, T., Chen, G., & Li, D. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460463
IoU-based overlapping metric and aggregated loss function for morphological-linear neural networks
Hernández, G., Rodríguez-Molina, A., Gómez, E. Z., Rojas-López, A. G., & Villarreal-Cervantes, M. G. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3797
Bajpai, A., & Srivastava, S. (2026) · Studies in computational intelligence · doi:10.1007/978-3-032-16711-8_1 · Cited by 2
Neural Network Compression and Knowledge Distillation
Ghojogh, B., & Ghodsi, A. (2026) · Springer eBooks · doi:10.1007/978-3-032-10738-1_20
Robertson, S., Diyan, M., & Alsmadi, H. (2026) · IEEE International Conference on Communication Systems and Network Technologies (CSNT) · doi:10.1109/csnt69054.2026.11502286
Mascione, D., Cristoforetti, M., Luca, A. D., Follega, F. M., Iuppa, R., & Saccardo, A. (2026) · Journal of Physics Conference Series · doi:10.1088/1742-6596/3206/1/012105
YORO (You Only Read Once): Automated Gauge Reading in Submarine Cabins via Head-Mounted Displays
Dong, X., Yin, X., Zhen, L., Jiang, C., Zhan, S., & Gu, Q. (2026) · Applied Sciences · doi:10.3390/app16104854
Energy Efficiency AI Models Through Quantization and Lightweight Architecture Design
Saikiran, N., Naidu, B. K., Latha, C. M., Sai, L. H. K., Shankar, M. K., & Ravikumar, G. (2026) · International Conference on Smart Electronic Devices and Intelligent Systems (ICSEDIS) · doi:10.1109/icsedis68157.2026.11518284
A Lightweight Deep Learning Model for Plant Disease Detection Using Quantized YOLOv8n
Smaali, R., Dendani, B., & Bahi, H. (2026) · IEEE International Conference on Complex Systems and Intelligent Computing (ICCSIC) · doi:10.1109/iccsic69301.2026.11521283
Zhao, H., Luan, M., Ranaweera, P. S., Liyanage, M., & Chang, Z. (2026) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2026.3694488 · Cited by 3
“This distinction necessitates a heterogeneous computing resource allocation scheme where the CSCC tasks are mapped to the most suitable processing unit [30].”
Balancing Accuracy and Energy: An Empirical Study of Optimal Subset Size Selection
Haddaji, O., Brun, O., & Prabhu, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-18494-8_11
Using Error Correction Code Schemes in Dependable Machine Learning Systems
Hu, J., Wang, X. R., Zhang, W., Guo, L., Liu, S., Reviriego, P., Gao, Z., & Lombardi, F. (2026) · Springer eBooks · doi:10.1007/978-3-032-17948-7_6
Patel, T., Kulkarni, C., Purushothaman, R., Kole, D., Parikh, M., & Keshava, R. (2026) · International Conference on Current Research in Artificial Intelligence and Data Science (ICCRAIDS) · doi:10.1109/iccraids67816.2026.11519729
Rao, S., & Bhavya Jyothi., A. (2026) · International Conference on Knowledge Engineering and Communication Systems (ICKECS) · doi:10.1109/ickecs70176.2026.11527624
Effective Lightweight Language Models for Edge Deployment in Low-Resource Settings
Panjolia, S., Chaudhary, A., Yadav, P., Uchoi, E., Singh, J., & Debbarma, K. (2026) · International Conference on Intelligent Systems in Engineering, Secured Systems and Cybersecurity (ICISESSC) · doi:10.1109/icisessc68634.2026.11542686
Dolphium: Co-Optimizing Quantization Dataflow and Paradigms on Poly-Hierarchical NPUs
Cui, X., Zhang, C., Chen, X., & Liang, Y. E. (2026) · Design, Automation, and Test in Europe · doi:10.23919/date69613.2026.11539577
Khaldy, M. A. A., Otaiwi, Z., & Al–Qerem, A. (2026) · International Conference on Computational Intelligence Approaches and Applications (ICCIAA) · doi:10.1109/icciaa68481.2026.11543764
“Model compression covers pruning, quantization, low-rank decomposition, and distillation [8].”
Canay, Ö. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6915201
Mu, J., Tan, B.-Y., Ren, J., Guo, M.-Y., Luo, C., & Bai, R.-B. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123768
Balzano, L., Ding, T., Haeffele, B. D., Kwon, S. M., Qu, Q., Wang, P., Wang, Z., & Yaras, C. B. (2026) · IEEE Signal Processing Magazine · doi:10.1109/msp.2026.3666749 · Cited by 1
“…cost (and a majority of the memory cost) in training deep networks involves dense linear layers of the form Y = W X , where X ∈ R d × n are the input activations (i.e., the batch of hidden feature vectors after passing through a nonlinearity from a previous layer), Y ∈ R d × n are output…”
Alecu, A. A. (2026) · Bioengineering · doi:10.3390/bioengineering13060683
“More broadly, model compression and efficiency-aware learning have been studied as key enablers of practical deployment [68].”
Gao, S., Zheng, X., Luo, D., Di, S., & Dong, W. (2026) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps65963.2026.00061
Low-Resource Generative AI: Model Optimization for Edge and Mobile Devices
Farooq, A., Bhowmick, N., Zahid, M., Asghar, M. A., & Amin, Y. (2026) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/1741
Potdar, P., Muchtar, F., Jaafar, A. G., Degan, K. S., Sulaiman, S., Sidik, M. K. M., Osman, M. Z., & Dawoodi, F. B. Y. P. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.085
Virtualized GPU Offloading for AI Inference: Enabling Deep Learning Frameworks on GPU-less Devices
Yu, W., Aslanidis, T., Gowda, D. K. T., Luo, X., Chatzopoulos, D., Montella, R., & Kosta, S. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587741 · Cited by 1
Explainable lightweight neural networks: A survey on methods, metrics, and challenges
Mushtaq, M., Madden, M. G., & Ullah, I. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134504 · Cited by 1
Kysil, V. M., Drachuk, O., Korol, A., Hnenna, V. O., & Zaitseva, E. (2025) · International Workshop on Intelligent Information Technologies & Systems of Information Security (IntelITSIS) · doi:10.55056/ceur-ws.org/vol-3963/paper13.pdf
“Other works [17-19] explore quantization and architectural optimizations to further enhance efficiency.”
StarCollab: An Adaptive Co-Optimization Framework for Efficient Space-Ground Collaboration
Li, Q., Zhao, K., Sheng, B., Wu, F., & Chen, G. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3716848
“Structural pruning [29], [30], [31], [32] is a widely adopted technique to compress deep neural networks for practical de-ployments on resource-limited platforms.”
Zhang, X., & Zhu, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7190900
HEADS: Accuracy--Makespan Co-Optimization for Multitenant Multi-FPGA Edge Systems
Kersz, I., Ely, A. F., Jordan, M. G., Azambuja, J. R., Kastensmidt, F. L., & Beck, A. C. S. (2026) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2026.3716149
“When accuracy is also considered, the problem becomes more complex, as model-level optimization techniques such as pruning and quantization introduce additional tradeo ff s between execution time, resource usage, and output quality that must be jointly managed [5], [6].”
Lightweight Channel Prediction for Low-Altitude UAV Communications via Knowledge Distillation
Lu, C., Shi, L., & Lan, R. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3718962
“The goal of this article is not to pursue state-of-the-art (SOTA) accuracy but to achieve a deployable performance-complexity balance under small sample sizes, low computational power, and high real-time constraints [13].”
Comparative Analysis of MobileNetV2 and EfficientNet for Real-Time Weather Image Classification
Mulyono, N. M. B. R. O., & Imaduddin, H. (2026) · International Conference on Smart Computing, IoT and Machine Learning (SIML) · doi:10.1109/siml69834.2026.11621298
Ensemble stacked model for the treatment and prevention of Arsenic induced Diabetes Mellitus
Riaz, A., & Khan, N. (2026) · Communications in Statistics Case Studies Data Analysis and Applications · doi:10.1080/23737484.2026.2695049
Huang, X., Li, Z., Li, Y., & Tang, S.-K. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-981-92-0607-0_28
Anju Anil, J., Rajarajan, Veena, K., Alkabbji, R., Kumar, S., & Karthikeyan, G. (2026) · International Conference on Data Science for Cyber-Physical Systems Resilience using Advanced Applications (ICDCA) · doi:10.1109/icdca69396.2026.11620044
Cui, L., Guo, Y., 彭纬璇, & Huang, Y. (2026) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/2575-8411.2026.00134
“Model compression techniques such as pruning, quantization, and knowledge distillation [22], [23] reduce the size of the model, and improve inference efficiency while maintaining its performance as much as possible.”
Gupta, S., Sultanpuri, C., Malya, R., Surpur, A., & Kulkarni, U. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-29325-1_11
Li, H., Liu, Z., Wang, Y., Huang, L., Zhang, J., Shao, D., Feng, T., Hao, X., & Wang, J. (2026) · Cold Regions Science and Technology · doi:10.1016/j.coldregions.2026.105097
Real-Time Motion Sickness Prediction on an Embedded System With Limited Resources
Colmenares, J. A. R., Mata-Carballeira, Ó., & Asua, E. (2026) · IEEE Access · doi:10.1109/access.2026.3722026
“While techniques like quantization and pruning exist [35], [36], and frameworks like TensorFlow Lite for Microcon-trollers facilitate deployment [37], these are predominantly focused on deep learning.”
Random Sparse Networks Training With Sharpness-Aware Regularization
Bai, Y., Zhang, M., Wang, H., Tao, Z., Li, K., Wang, Y., & Fu, Y. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3722118
A Study on Image Recognition Technologies for Lightweight Autonomous Robots
Zhou, Y. (2026) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1109/eitce70137.2026.11634300
Zhang, J., & Shang, J. (2026) · Algorithms · doi:10.3390/a19080670
Bhardwaj, Y., & Sharma, A. (2026) · International Conference on Sustainable Computing and Smart Systems (ICSCSS) · doi:10.1109/icscss69635.2026.11645626
A real-time surface defect detection framework for synthetic-fiber bobbins
Xue, H., Zhang, Z., 达飞鹏, & Gai, S. (2026) · Journal of Engineered Fibers and Fabrics · doi:10.1177/15589250261478091
FPGA Implementation of CNN for Digit Recognition
Choudhary, A., Kumar, A., Bhuyan, M. K., Kumar, S., & Raj, S. (2026) · IEEE Guwahati Subsection Conference (GCON) · doi:10.1109/gcon69192.2026.11649374
Kumar, R., Baranwal, N., & Singh, A. K. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106150
A Comprehensive Approach to Tomato Leaf Disease Classification Using Deep Learning
Rambani, S., & Katiyar, K. (2026) · International Conference on Power, Control and Computing Technologies (ICPC2T) · doi:10.1109/icpc2t68221.2026.11646203
Contextually Adaptive AI-BIM for Sustainable Construction
Athas, S. I. A., Najafi, F., & Nawari, N. (2026) · ASEE Annual Conference & Exposition · doi:10.18260/1-2--59097
Improving Performance–Efficiency Trade-offs Through Model Compression and Optimization Strategies
Archana, D. U. S. (2026) · International Journal of Research & Technology · doi:10.64882/ijrt.v14.i3.1755
Zhang, S., Ma, J., Chi, K., Liu, J., & Shi, Z. (2026) · ACM Transactions on Sensor Networks · doi:10.1145/3838798
Barot, V. G., Patel, M. R., Patel, M. R., & Barot, P. (2026) · Journal of Computational and Applied Mathematics · doi:10.1016/j.cam.2026.118114
On-board efficiency: comparing compressed deep learning and classical models for Earth observation
Palma, G. D., Pardini, A., Li, L., Pompei, G., Coppola, M., Caro, V. D., & Lomonaco, V. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01720-0
“Techniques for compressing models, such as pruning, quantization, low-rank decomposition, and knowledge distillation, have received extensive attention in the field of deep learning [9, 22, 26].”
Zhang, Z., Wang, Y., Zhang, L., Chen, D., Zhang, W., Li, F., & Zhou, J. (2026) · Med Research · doi:10.1002/mdr2.70088
Ahmed, A. A., Adeshina, S. A., Aleshinloye, Y. A., Ogundokun, R. O., & Owolawi, P. A. (2026) · Intelligence-Based Medicine · doi:10.1016/j.ibmed.2026.100475
Metadata
- Authors
- Cheng, Y., Wang, D., Zhou, P., & Zhang, T.
- Affiliations
- IBM Research - Thomas J. Watson Research Center (US)
- Harbin Institute of Technology (CN)
- Huazhong University of Science and Technology (CN)
- Tsinghua University (CN)
- Venue
- IEEE Signal Processing Magazine
- Published
- 2018-01
- Volume
- 35
- Issue
- 1
- Pages
- 126-136
- ISSN
- 1053-5888 (ISSN-L)
- 1558-0792
- OpenAlex
- W2783538964
- Cited by
- 817
- References
- 67
- Citations by year
- 2026: 114 · 2025: 132 · 2024: 116 · 2023: 110 · 2022: 109 · 2021: 92 · 2020: 89 · 2019: 41 · 2018: 14
- FWCI
- 29.51
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- 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 › Stochastic Gradient Optimization Techniques
- Keywords
- model compression, deep neural network, inference acceleration, parameter reduction, convolutional neural networks, training efficiency, GPU computing, face verification
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.