{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:20:30Z","timestamp":1785604830787,"version":"3.56.0"},"reference-count":209,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3182659","type":"journal-article","created":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T20:37:15Z","timestamp":1655152635000},"page":"63280-63300","source":"Crossref","is-referenced-by-count":202,"title":["Methods for Pruning Deep Neural Networks"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6041-2646","authenticated-orcid":false,"given":"Sunil","family":"Vadera","sequence":"first","affiliation":[{"name":"School of Science, Engineering and Environment, University of Salford, Salford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salem","family":"Ameen","sequence":"additional","affiliation":[{"name":"School of Science, Engineering and Environment, University of Salford, Salford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2962338"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1799-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3234150"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907373117"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref9","first-page":"107","article-title":"Skeletonization: A technique for trimming the fat from a network via relevance assessment","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Mozer"},{"key":"ref10","first-page":"120","article-title":"Creating local and distributed bottlenecks in hidden layers of back-propagation networks","volume-title":"Proc. Connectionist Models Summer School","author":"Kruschke"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/72.248452"},{"key":"ref12","first-page":"519","article-title":"A back-propagation algorithm with optimal use of hidden units","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chauvin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/b978-1-4832-1448-1.50016-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155287"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486540"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.6.910"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2019.00-68"},{"key":"ref19","first-page":"1","article-title":"Reducing duplicate filters in deep neural networks","volume-title":"Proc. NIPS Workshop Deep Learning: Bridging Theory Pract.","author":"RoyChowdhury"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80037-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451123"},{"key":"ref22","first-page":"506","article-title":"Optimal brain damage","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"89","author":"LeCun"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"ref24","first-page":"263","article-title":"Optimal brain surgeon: Extensions and performance comparison","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Hassibi"},{"key":"ref25","article-title":"RandomOut: Using a convolutional gradient norm to rescue convolutional filters","author":"Cohen","year":"2016","journal-title":"arXiv:1602.05931"},{"key":"ref26","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","author":"Lee","year":"2018","journal-title":"arXiv:1810.02340"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/336"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref30","first-page":"1","article-title":"Do deep convolutional nets really need to be deep and convolutional","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Urban"},{"key":"ref31","article-title":"SCAN: A scalable neural networks framework towards compact and efficient models","author":"Zhang","year":"2019","journal-title":"arXiv:1906.03951"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref35","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","author":"Zhou","year":"2017","journal-title":"arXiv:1702.03044"},{"key":"ref36","first-page":"5585","article-title":"Focused quantization for sparse CNNs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref37","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or \u22121","author":"Courbariaux","year":"2016","journal-title":"arXiv:1602.02830"},{"key":"ref38","first-page":"2285","article-title":"Compressing neural networks with the hashing trick","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref40","article-title":"Designing neural network architectures using reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Baker"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2019.2914438"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00936"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/94"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00257"},{"key":"ref46","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zoph"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898092"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3212725.3212733"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3371425.3371481"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24425\/bpas.2018.125927"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3578938"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3413.001.0001"},{"key":"ref54","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2906563"},{"issue":"56","key":"ref57","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00289"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref62","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09825-6"},{"key":"ref64","article-title":"Learning both weights and connections for efficient neural networks","author":"Han","year":"2015","journal-title":"arXiv:1506.02626"},{"key":"ref65","first-page":"1387","article-title":"Dynamic network surgery for efficient DNNs","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref66","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Frankle"},{"key":"ref67","article-title":"Rethinking the value of network pruning","volume-title":"Proc. 7th Int. Conf. Learn. Represent., (ICLR)","author":"Liu"},{"key":"ref68","article-title":"Stabilizing the lottery ticket hypothesis","author":"Frankle","year":"2019","journal-title":"arXiv:1903.01611"},{"key":"ref69","first-page":"4932","article-title":"One ticket to win them all: Generalizing lottery ticket initializations across datasets and optimizers","volume-title":"Proc. Neural Inf. Process. Syst. (NeuralPS)","author":"Ari Morcos"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3378184.3378224"},{"key":"ref71","article-title":"Playing the lottery with rewards and multiple languages: Lottery tickets in RL and NLP","author":"Yu","year":"2019","journal-title":"arXiv:1906.02768"},{"key":"ref72","article-title":"Pointer sentinel mixture models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Merity"},{"key":"ref73","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Vaswani"},{"key":"ref74","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref76","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. 5th Int. Conf. Learn. Represent., (ICLR)","author":"Li"},{"key":"ref77","first-page":"2148","article-title":"Predicting parameters in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Denil"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.04.021"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2494536"},{"key":"ref80","article-title":"Network in a network","volume-title":"Proc. 2nd Int. Conf. Learn. Represent. (ICLR)","author":"Lin"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"ref82","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv:1412.6550"},{"key":"ref83","article-title":"An entropy-based pruning method for CNN compression","author":"Luo","year":"2017","journal-title":"arXiv:1706.05791"},{"key":"ref84","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016","journal-title":"arXiv:1607.03250"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084206"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487623"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref91","article-title":"Approximated Oracle filter pruning for destructive CNN width optimization","author":"Ding","year":"2019","journal-title":"arXiv:1905.04748"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00083"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref95","article-title":"Structured probabilistic pruning for convolutional neural network acceleration","author":"Wang","year":"2017","journal-title":"arXiv:1709.06994"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107461"},{"key":"ref97","article-title":"Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers","author":"Ye","year":"2018","journal-title":"arXiv:1802.00124"},{"key":"ref98","article-title":"A deep neural network compression pipeline: Pruning, quantization, Huffman encoding","volume-title":"Proc. ICLR","author":"Han"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_14"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00291"},{"key":"ref101","first-page":"6566","article-title":"EigenDamage: Structured pruning in the kronecker-factored eigenbasis","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref102","volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","author":"Bishop","year":"2006"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1331\/table-5"},{"key":"ref104","first-page":"145","article-title":"Parallel networks that learn to pronounce English text","volume":"1","author":"Sejnowski","year":"1987","journal-title":"Complex Syst."},{"key":"ref105","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"Molchanov","year":"2016","journal-title":"arXiv:1611.06440"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref107","first-page":"573","article-title":"A Kronecker-factored approximate Fisher matrix for convolution layers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Grosse"},{"key":"ref108","first-page":"5113","article-title":"Collaborative channel pruning for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/318"},{"key":"ref111","first-page":"4860","article-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Dong"},{"key":"ref112","first-page":"875","article-title":"Discrimination-aware channel pruning for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhuang"},{"key":"ref113","article-title":"Globally soft filter pruning for efficient convolutional neural networks","author":"Xu","year":"2018"},{"key":"ref114","first-page":"6778","article-title":"Structured Bayesian pruning via log-normal multiplicative noise","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Neklyudov"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01131"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.31"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.525"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxz078"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-018-01001-9"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01464"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.3.543"},{"key":"ref122","first-page":"177","article-title":"Comparing biases for minimal network construction with back-propagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hanson"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986721"},{"key":"ref124","first-page":"3180","article-title":"Net-trim: Convex pruning of deep neural networks with performance guarantee","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Aghasi"},{"key":"ref125","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"Zhu","year":"2017","journal-title":"arXiv:1710.01878"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_25"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205295"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/330"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3234804.3234824"},{"key":"ref130","article-title":"Demystifying neural network filter pruning","author":"Qin","year":"2018","journal-title":"arXiv:1811.02639"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00071"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_12"},{"key":"ref133","first-page":"6379","article-title":"Global sparse momentum SGD for pruning very deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref134","article-title":"Sparse networks from scratch: Faster training without losing performance","author":"Dettmers","year":"2019","journal-title":"arXiv:1907.04840"},{"key":"ref135","first-page":"1283","article-title":"Model compression with adversarial robustness: A unified optimization framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gui"},{"key":"ref136","article-title":"Latent weights do not exist: Rethinking binarized neural network optimization","author":"Helwegen","year":"2019","journal-title":"arXiv:1906.02107"},{"key":"ref137","first-page":"7344","article-title":"Normalization helps training of quantized LSTM","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/3349569.3351537"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00721"},{"key":"ref140","first-page":"963","article-title":"Point-voxel CNN for efficient 3D deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref141","first-page":"6179","article-title":"Deep model transferability from attribution maps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref142","first-page":"2561","article-title":"Positive-unlabeled compression on the cloud","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref143","article-title":"Deconstructing lottery tickets: Zeros, signs, and the supermask","author":"Zhou","year":"2019","journal-title":"arXiv:1905.01067"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350928"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375385"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371849"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378534"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_28"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00508"},{"key":"ref150","article-title":"Training compact CNNs for image classification using dynamic-coded filter fusion","author":"Lin","year":"2021","journal-title":"arXiv:2107.06916"},{"key":"ref151","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hassibi"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1007\/11759966_78"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77002-2_2"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2009.5346186"},{"key":"ref155","article-title":"Optimizing deep learning networks using multi-armed bandits","author":"Ameen","year":"2017"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1145\/3089801.3089806"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00890"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1145\/3212725.3212730"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3377713.3377739"},{"key":"ref161","first-page":"5564","article-title":"An adaptive empirical Bayesian method for sparse deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Deng"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1145\/3307681.3326608"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1145\/3299874.3319492"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1145\/3287624.3287643"},{"key":"ref165","first-page":"13681","article-title":"AutoPrune: Automatic network pruning by regularizing auxiliary parameters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1145\/3366750.3366751"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00932"},{"key":"ref168","article-title":"Network pruning via transformable architecture search","author":"Dong","year":"2019","journal-title":"arXiv:1905.09717"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415117"},{"key":"ref170","article-title":"Distilling large language models into tiny and effective students using pQRNN","author":"Kaliamoorthi","year":"2021","journal-title":"arXiv:2101.08890"},{"key":"ref171","article-title":"Speeding-up convolutional neural networks using fine-tuned CP-decomposition","author":"Lebedev","year":"2014","journal-title":"arXiv:1412.6553"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2873305"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref174","article-title":"Improving the speed of neural networks on cpus","volume-title":"Proc. Deep Learn. Unsupervised Feature Learn. Workshop, Neural Inf. Process. Syst.","author":"Vanhoucke"},{"key":"ref175","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref176","article-title":"Compressing deep convolutional networks using vector quantization","author":"Gong","year":"2014","journal-title":"arXiv:1412.6115"},{"key":"ref177","first-page":"4114","article-title":"Binarized neural networks","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Hubara"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref179","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","author":"Krishnamoorthi","year":"2018","journal-title":"arXiv:1806.08342"},{"key":"ref180","first-page":"1043","article-title":"Frequency-domain dynamic pruning for convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00821"},{"key":"ref182","first-page":"7948","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Banner"},{"key":"ref183","first-page":"3918","article-title":"MetaQuant: Learning to quantize by learning to penetrate non-differentiable quantization","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref184","first-page":"9847","article-title":"Towards accurate post-training network quantization via bit-split and stitching","volume-title":"Proc. Mach. Learn. Res.","volume":"119","author":"Wang"},{"key":"ref185","article-title":"Training with quantization noise for extreme model compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fan"},{"key":"ref186","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref187","first-page":"2178","article-title":"Runtime neural pruning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00171"},{"key":"ref189","article-title":"MONAS: Multi-objective neural architecture search using reinforcement learning","author":"Hsu","year":"2018","journal-title":"arXiv:1806.10332"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref191","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Pham"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref194","first-page":"292","article-title":"Eager pruning: Algorithm and architecture support for fast training of deep neural networks","volume-title":"Proc. 46th Int. Symp. Comput. Archit.","author":"Zhang"},{"key":"ref195","first-page":"2943","article-title":"Rigging the lottery: Making all tickets winners","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Evci"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700789"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref201","article-title":"Labeled faces in the wild: A database forstudying face recognition in unconstrained environments","volume-title":"Proc. Workshop Faces Real-Life\u2019Images, Detection, Alignment, Recognit.","author":"Huang"},{"key":"ref202","volume-title":"The CIFAR-10 and CIFAR-100 Datasets","author":"Krizhevsky","year":"2009"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref205","volume-title":"The CALTECH-UCSD Birds-200-2011 Dataset","author":"Wah","year":"2011"},{"key":"ref206","first-page":"487","article-title":"Learning deep features for scene recognition using places database","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref207","article-title":"Learning face representation from scratch","author":"Yi","year":"2014","journal-title":"arXiv:1411.7923"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3302"},{"key":"ref209","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09795013.pdf?arnumber=9795013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:32:44Z","timestamp":1706761964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9795013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":209,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3182659","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}