{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T23:50:02Z","timestamp":1771804202858,"version":"3.50.1"},"reference-count":41,"publisher":"Tech Science Press","issue":"2","license":[{"start":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T00:00:00Z","timestamp":1723939200000},"content-version":"vor","delay-in-days":230,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2024]]},"DOI":"10.32604\/cmc.2024.053632","type":"journal-article","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T08:08:07Z","timestamp":1722586087000},"page":"3021-3045","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":3,"title":["A Novel Quantization and Model Compression Approach for Hardware Accelerators in Edge Computing"],"prefix":"10.32604","volume":"80","author":[{"given":"Fangzhou","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dingjiang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"17807","published-online":{"date-parts":[[2024]]},"reference":[{"key":"ref1","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","first-page":"2704","article-title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference, Quantization and training of neural networks for efficient integer-arithmetic-only inference","author":"Jacob","year":"Jun. 18, 2018"},{"key":"ref2","unstructured":"Q. Jin et al., \u201cF8Net: Fixed-point 8-bit only multiplication for network quantization,\u201d arXiv preprint arXiv:2202.05239, 2022."},{"key":"ref3","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops","first-page":"696","article-title":"LSQ+: Improving low-bit quantization through learnable offsets and better initialization","author":"Bhalgat","year":"Jun. 14, 2020"},{"key":"ref4","series-title":"Int. Conf. Learn. Represent.","article-title":"A block minifloat representation for training deep neural networks","author":"Fox","year":"May 3, 2021"},{"key":"ref5","series-title":"Comput. Vis.\u2013ECCV 2020: 16th Eur. Conf.","first-page":"430","article-title":"Profit: A novel training method for sub-4-bit mobilenet models","author":"Park","year":"2020"},{"key":"ref6","unstructured":"A. Zhou, A. Yao, Y. Guo, L. Xu, and Y. Chen, \u201cIncremental network quantization: Towards lossless cnns with low-precision weights,\u201d arXiv preprint arXiv:1702.03044, 2017."},{"key":"ref7","unstructured":"J. Choi, Z. Wang, S. Venkataramani, P. I. -J. Chuang, V. Srinivasan and K. Gopalakrishnan, \u201cPACT: Parameterized clipping activation for quantized neural networks,\u201d arXiv preprint arXiv:1805.06085, 2018."},{"key":"ref8","unstructured":"Y. Li, X. Dong, and W. Wang, \u201cAdditive powers-of-two quantization: An efficient non-uniform discretization for neural networks,\u201d arXiv preprint arXiv:1909.13144, 2019."},{"key":"ref9","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"2359","article-title":"Deepshift: Towards multiplication-less neural networks","author":"Elhoushi","year":"Jun. 20, 2021"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1109\/JSTSP.2020.3005030","article-title":"Iteratively training look-up tables for network quantization","volume":"14","author":"Cardinaux","year":"May 2020","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref11","unstructured":"S. Han, H. Mao, and W. J. Dally, \u201cDeep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,\u201d arXiv preprint arXiv:1510.00149, 2015."},{"key":"ref12","unstructured":"Y. Gong, L. Liu, M. Yang, and L. Bourdev, \u201cCompressing deep convolutional networks using vector quantization,\u201d arXiv preprint arXiv:1412.6115, 2014."},{"key":"ref13","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1109\/JSTSP.2020.2975903","article-title":"Universal deep neural network compression","volume":"14","author":"Choi","year":"2020","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3431815","article-title":"Lane compression: A lightweight lossless compression method for machine learning on embedded systems","volume":"20","author":"Ko","year":"2021","journal-title":"ACM Trans. Embedded Comput. Syst. (TECS)"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3358205","article-title":"Memory- and communication-aware model compression for distributed deep learning inference on IoT","volume":"18","author":"Bhardwaj","year":"2019","journal-title":"ACM Trans. Embedded Comput. Syst. (TECS)"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3391901","article-title":"EncoDeep: Realizing bit-flexible encoding for deep neural networks","volume":"19","author":"Samragh","year":"2020","journal-title":"ACM Trans. Embedded Comput. Syst. (TECS)"},{"key":"ref17","series-title":"Proc. 2019 11th Int. Conf. Mach. Learn. Comput.","first-page":"1","article-title":"Model loss and distribution analysis of regression problems in machine learning","author":"Yang","year":"Feb. 22, 2019"},{"key":"ref18","first-page":"1","article-title":"Early stopping for iterative regularization with general loss functions","volume":"23","author":"Hu","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","first-page":"9117","article-title":"Rethinking feature distribution for loss functions in image classification","author":"Wan","year":"Jun. 18, 2018"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"7832","DOI":"10.1109\/TCSVT.2022.3186041","article-title":"Adaptive weighted losses with distribution approximation for efficient consistency-based semi-supervised learning","volume":"32","author":"Li","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref21","series-title":"2021 Int. Joint Conf. Neur. Netw. (IJCNN)","first-page":"1","article-title":"Learning to binarize convolutional neural networks with adaptive neural encoder","author":"Zhang","year":"Jul. 18, 2021"},{"key":"ref22","series-title":"Proc. 55th Annu. Des. Automat. Conf.","first-page":"1","article-title":"Compensated-DNN: Energy efficient low-precision deep neural networks by compensating quantization errors","author":"Jain","year":"Jun. 24, 2018"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1109\/TC.2020.2995593","article-title":"VecQ: Minimal loss DNN model compression with vectorized weight quantization","volume":"70","author":"Gong","year":"2020","journal-title":"IEEE Trans. Comput."},{"key":"ref24","doi-asserted-by":"crossref","first-page":"3880","DOI":"10.1109\/TNNLS.2020.3016078","article-title":"General plane-based clustering with distribution loss","volume":"32","author":"Wang","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref25","series-title":"2019 IEEE 27th Annu. Int. Symp. Field-Programmable Custom Comput. Mach. (FCCM)","first-page":"26","article-title":"LUTNet: Rethinking inference in fpga soft logic","author":"Wang","year":"Apr. 28, 2019"},{"key":"ref26","unstructured":"Y. Bengio, N. L\u00e9onard, and A. Courville, \u201cEstimating or propagating gradients through stochastic neurons for conditional computation,\u201d arXiv preprint arXiv:1308.3432, 2013."},{"key":"ref27","unstructured":"A. Lempel and J. Ziv, \u201cLempel-ziv\u2013markov chain algorithm,\u201d Accessed: Dec. 7, 2023. [Online]. Available: https:\/\/en.wikipedia.org\/wiki\/Lempel-Ziv-Markov_chain_algorithm"},{"key":"ref28","unstructured":"A. Krizhevsky and G. Hinton, \u201cLearning multiple layers of features from tiny images,\u201d Accessed: Dec. 7, 2023. 2009. [Online]. Available: http:\/\/www.cs.utoronto.ca\/~kriz\/learning-features-2009-TR.pdf"},{"key":"ref29","series-title":"2009 IEEE Conf. Comput. Vis. Pattern Recognit.","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"Deng","year":"Jun. 22, 2009"},{"key":"ref30","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","first-page":"2852","article-title":"Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild","author":"Li","year":"Jul. 22, 2017"},{"key":"ref31","series-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","first-page":"722","article-title":"Bi-real Net: Enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algorithm","author":"Liu","year":"Sep. 8, 2018"},{"key":"ref32","unstructured":"V. Sovrasov, \u201cptflops: A flops counting tool for neural networks in pytorch framework,\u201d Accessed: Dec. 7, 2023. 2020. [Online]. Available: https:\/\/github.com\/sovrasov\/flops-counter.pytorch"},{"key":"ref33","series-title":"Adv. Neur. Inf. Process. Syst.","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume":"29","author":"Salimans","year":"Dec. 5, 2016"},{"key":"ref34","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"4350","article-title":"Learning to quantize deep networks by optimizing quantization intervals with task loss","author":"Jung","year":"Jun. 16, 2019"},{"key":"ref35","unstructured":"D. Miyashita, E. H. Lee, and B. Murmann, \u201cConvolutional neural networks using logarithmic data representation,\u201d arXiv preprint arXiv:1603.01025, 2016."},{"key":"ref36","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"Jun. 30, 2016"},{"key":"ref37","unstructured":"Y. Idelbayev, \u201cProper ResNet implementation for CIFAR10\/CIFAR100 in PyTorch,\u201d Accessed: Dec. 7, 2023. 2020. [Online]. Available: https:\/\/github.com\/akamaster\/pytorch_resnet_cifar10"},{"key":"ref38","series-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","first-page":"365","article-title":"LQ-Nets: Learned quantization for highly accurate and compact deep neural networks","author":"Zhang","year":"Sep. 8, 2018"},{"key":"ref39","unstructured":"F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally and K. Keutzer, \u201cSqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 mb model size,\u201d arXiv preprint arXiv:1602.07360, 2016."},{"key":"ref40","series-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","first-page":"116","article-title":"ShuffleNet v2: Practical guidelines for efficient CNN architecture design","author":"Ma","year":"Sep. 8, 2018"},{"key":"ref41","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"6897","article-title":"Suppressing uncertainties for large-scale facial expression recognition","author":"Wang","year":"Jun. 13, 2020"}],"container-title":["Computers, Materials &amp; Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.techscience.com\/files\/cmc\/2024\/TSP_CMC-80-2\/TSP_CMC_53632\/TSP_CMC_53632.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T12:24:32Z","timestamp":1741263872000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v80n2\/57644"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":41,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024]]},"published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2024.053632","relation":{},"ISSN":["1546-2226"],"issn-type":[{"value":"1546-2226","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2024-05-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-14","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-15","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}