14.5.8.6.8 Neural Net Quantization

Chapter Contents (Back)
CNN. Efficient Implementation. Quantization.

Dong, Y.P.[Yin-Peng], Ni, R.K.[Ren-Kun], Li, J.G.[Jian-Guo], Chen, Y.R.[Yu-Rong], Su, H.[Hang], Zhu, J.[Jun],
Stochastic Quantization for Learning Accurate Low-Bit Deep Neural Networks,
IJCV(127), No. 11-12, December 2019, pp. 1629-1642.
Springer DOI 1911
BibRef

Zhou, A.[Aojun], Yao, A.B.[An-Bang], Wang, K.[Kuan], Chen, Y.R.[Yu-Rong],
Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks,
CVPR18(9426-9435)
IEEE DOI 1812
Computer vision, Pattern recognition BibRef

Zhou, Z.G.[Zheng-Guang], Zhou, W.G.[Wen-Gang], Lv, X.T.[Xu-Tao], Huang, X.[Xuan], Wang, X.Y.[Xiao-Yu], Li, H.Q.[Hou-Qiang],
Progressive Learning of Low-Precision Networks for Image Classification,
MultMed(23), 2021, pp. 871-882.
IEEE DOI 2103
Quantization (signal), Training, Neural networks, Convolution, Acceleration, Task analysis, Complexity theory, image classification BibRef

Chu, T.[Tianshu], Luo, Q.[Qin], Yang, J.[Jie], Huang, X.L.[Xiao-Lin],
Mixed-precision quantized neural networks with progressively decreasing bitwidth,
PR(111), 2021, pp. 107647.
Elsevier DOI 2012
Model compression, Quantized neural networks, Mixed-precision BibRef


Liu, H.Y.[Hong-Yang], Elkerdawy, S.[Sara], Ray, N.[Nilanjan], Elhoushi, M.[Mostafa],
Layer Importance Estimation with Imprinting for Neural Network Quantization,
MAI21(2408-2417)
IEEE DOI 2109
Training, Quantization (signal), Search methods, Neural networks, Estimation, Reinforcement learning, Pattern recognition BibRef

Yun, S.[Stone], Wong, A.[Alexander],
Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics,
MAI21(2447-2456)
IEEE DOI 2109
Degradation, Training, Quantization (signal), Systematics, Fluctuations, Dynamic range, Robustness BibRef

Fournarakis, M.[Marios], Nagel, M.[Markus],
In-Hindsight Quantization Range Estimation for Quantized Training,
ECV21(3057-3064)
IEEE DOI 2109
Training, Quantization (signal), Tensors, Neural networks, Estimation, Dynamic range, Benchmark testing BibRef

Yu, H.[Haichao], Yang, L.J.[Lin-Jie], Shi, H.[Humphrey],
Is In-Domain Data Really Needed? A Pilot Study on Cross-Domain Calibration for Network Quantization,
ECV21(3037-3046)
IEEE DOI 2109
Knowledge engineering, Training, Quantization (signal), Ultrasonic imaging, Sensitivity, Satellites, Calibration BibRef

Langroudi, H.F.[Hamed F.], Karia, V.[Vedant], Carmichael, Z.[Zachariah], Zyarah, A.[Abdullah], Pandit, T.[Tej], Gustafson, J.L.[John L.], Kudithipudi, D.[Dhireesha],
Alps: Adaptive Quantization of Deep Neural Networks with GeneraLized PositS,
ECV21(3094-3103)
IEEE DOI 2109
Deep learning, Quantization (signal), Adaptive systems, Upper bound, Numerical analysis, Heuristic algorithms, Pattern recognition BibRef

Abdolrashidi, A.[AmirAli], Wang, L.[Lisa], Agrawal, S.[Shivani], Malmaud, J.[Jonathan], Rybakov, O.[Oleg], Leichner, C.[Chas], Lew, L.[Lukasz],
Pareto-Optimal Quantized ResNet Is Mostly 4-bit,
ECV21(3085-3093)
IEEE DOI 2109
Training, Analytical models, Quantization (signal), Computational modeling, Neural networks, Libraries, Hardware BibRef

Trusov, A.[Anton], Limonova, E.[Elena], Slugin, D.[Dmitry], Nikolaev, D.[Dmitry], Arlazarov, V.V.[Vladimir V.],
Fast Implementation of 4-bit Convolutional Neural Networks for Mobile Devices,
ICPR21(9897-9903)
IEEE DOI 2105
Performance evaluation, Quantization (signal), Neural networks, Time measurement, Real-time systems, convolutional neural networks BibRef

Hacene, G.B.[Ghouthi Boukli], Lassance, C.[Carlos], Gripon, V.[Vincent], Courbariaux, M.[Matthieu], Bengio, Y.[Yoshua],
Attention Based Pruning for Shift Networks,
ICPR21(4054-4061)
IEEE DOI 2105
Deep learning, Training, Quantization (signal), Convolution, Computer architecture, Transforms, Complexity theory BibRef

Hou, Z.[Zejiang], Kung, S.Y.[Sun-Yuan],
A Discriminant Information Approach to Deep Neural Network Pruning,
ICPR21(9553-9560)
IEEE DOI 2105
Quantization (signal), Power measurement, Image coding, Neural networks, Tools, Benchmark testing, Pattern recognition BibRef

Marinó, G.C.[Giosuè Cataldo], Ghidoli, G.[Gregorio], Frasca, M.[Marco], Malchiodi, D.[Dario],
Compression strategies and space-conscious representations for deep neural networks,
ICPR21(9835-9842)
IEEE DOI 2105
Quantization (signal), Source coding, Computational modeling, Neural networks, Random access memory, Probabilistic logic, drug-target prediction BibRef

Yuan, Y.[Yong], Chen, C.[Chen], Hu, X.[Xiyuan], Peng, S.[Silong],
Towards Low-Bit Quantization of Deep Neural Networks with Limited Data,
ICPR21(4377-4384)
IEEE DOI 2105
Training, Quantization (signal), Sensitivity, Neural networks, Object detection, Data models, Complexity theory BibRef

Dbouk, H.[Hassan], Sanghvi, H.[Hetul], Mehendale, M.[Mahesh], Shanbhag, N.[Naresh],
DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks,
ECCV20(XXVII:90-106).
Springer DOI 2011
BibRef

do Nascimento, M.G.[Marcelo Gennari], Costain, T.W.[Theo W.], Prisacariu, V.A.[Victor Adrian],
Finding Non-uniform Quantization Schemes Using Multi-task Gaussian Processes,
ECCV20(XVII:383-398).
Springer DOI 2011
BibRef

Neumann, D., Sattler, F., Kirchhoffer, H., Wiedemann, S., Müller, K., Schwarz, H., Wiegand, T., Marpe, D., Samek, W.,
Deepcabac: Plug Play Compression of Neural Network Weights and Weight Updates,
ICIP20(21-25)
IEEE DOI 2011
Artificial neural networks, Quantization (signal), Image coding, Training, Servers, Compression algorithms, Neural Networks, Distributed Training BibRef

Haase, P., Schwarz, H., Kirchhoffer, H., Wiedemann, S., Marinc, T., Marban, A., Müller, K., Samek, W., Marpe, D., Wiegand, T.,
Dependent Scalar Quantization For Neural Network Compression,
ICIP20(36-40)
IEEE DOI 2011
Quantization (signal), Indexes, Neural networks, Context modeling, Entropy coding, Image reconstruction, neural network compression BibRef

Kwon, S.J., Lee, D., Kim, B., Kapoor, P., Park, B., Wei, G.,
Structured Compression by Weight Encryption for Unstructured Pruning and Quantization,
CVPR20(1906-1915)
IEEE DOI 2008
Sparse matrices, Decoding, Quantization (signal), Viterbi algorithm, Bandwidth, Encryption BibRef

Jung, J., Kim, J., Kim, Y., Kim, C.,
Reinforcement Learning-Based Layer-Wise Quantization For Lightweight Deep Neural Networks,
ICIP20(3070-3074)
IEEE DOI 2011
Quantization (signal), Neural networks, Learning (artificial intelligence), Computational modeling, Embedded system BibRef

Geng, X., Lin, J., Li, S.,
Cascaded Mixed-Precision Networks,
ICIP20(241-245)
IEEE DOI 2011
Neural networks, Quantization (signal), Training, Network architecture, Optimization, Image coding, Schedules, Pruning BibRef

Fang, J.[Jun], Shafiee, A.[Ali], Abdel-Aziz, H.[Hamzah], Thorsley, D.[David], Georgiadis, G.[Georgios], Hassoun, J.H.[Joseph H.],
Post-training Piecewise Linear Quantization for Deep Neural Networks,
ECCV20(II:69-86).
Springer DOI 2011
BibRef

Xie, Z.[Zheng], Wen, Z.Q.[Zhi-Quan], Liu, J.[Jing], Liu, Z.Q.[Zhi-Qiang], Wu, X.X.[Xi-Xian], Tan, M.K.[Ming-Kui],
Deep Transferring Quantization,
ECCV20(VIII:625-642).
Springer DOI 2011
BibRef

Wang, Y.[Ying], Lu, Y.D.[Ya-Dong], Blankevoort, T.[Tijmen],
Differentiable Joint Pruning and Quantization for Hardware Efficiency,
ECCV20(XXIX: 259-277).
Springer DOI 2010
BibRef

Cai, Y.H.[Yao-Hui], Yao, Z.W.[Zhe-Wei], Dong, Z.[Zhen], Gholami, A.[Amir], Mahoney, M.W.[Michael W.], Keutzer, K.[Kurt],
ZeroQ: A Novel Zero Shot Quantization Framework,
CVPR20(13166-13175)
IEEE DOI 2008
Quantization (signal), Training, Computational modeling, Sensitivity, Artificial neural networks, Task analysis, Training data BibRef

Qu, Z., Zhou, Z., Cheng, Y., Thiele, L.,
Adaptive Loss-Aware Quantization for Multi-Bit Networks,
CVPR20(7985-7994)
IEEE DOI 2008
Quantization (signal), Optimization, Neural networks, Adaptive systems, Microprocessors, Training, Tensile stress BibRef

Jin, Q., Yang, L., Liao, Z.,
AdaBits: Neural Network Quantization With Adaptive Bit-Widths,
CVPR20(2143-2153)
IEEE DOI 2008
Adaptation models, Quantization (signal), Training, Neural networks, Biological system modeling, Adaptive systems BibRef

Zhu, F.[Feng], Gong, R.H.[Rui-Hao], Yu, F.W.[Feng-Wei], Liu, X.L.[Xiang-Long], Wang, Y.F.[Yan-Fei], Li, Z.L.[Zhe-Long], Yang, X.Q.[Xiu-Qi], Yan, J.J.[Jun-Jie],
Towards Unified INT8 Training for Convolutional Neural Network,
CVPR20(1966-1976)
IEEE DOI 2008
Training, Quantization (signal), Convergence, Acceleration, Computer crashes, Optimization, Task analysis BibRef

Zhuang, B., Liu, L., Tan, M., Shen, C., Reid, I.D.,
Training Quantized Neural Networks With a Full-Precision Auxiliary Module,
CVPR20(1485-1494)
IEEE DOI 2008
Training, Quantization (signal), Object detection, Detectors, Computational modeling, Task analysis, Neural networks BibRef

Yu, H., Wen, T., Cheng, G., Sun, J., Han, Q., Shi, J.,
Low-bit Quantization Needs Good Distribution,
EDLCV20(2909-2918)
IEEE DOI 2008
Quantization (signal), Training, Task analysis, Pipelines, Adaptation models, Computational modeling, Neural networks BibRef

Bhalgat, Y., Lee, J., Nagel, M., Blankevoort, T., Kwak, N.,
LSQ+: Improving low-bit quantization through learnable offsets and better initialization,
EDLCV20(2978-2985)
IEEE DOI 2008
Quantization (signal), Training, Clamps, Neural networks, Artificial intelligence, Computer architecture, Minimization BibRef

Pouransari, H., Tu, Z., Tuzel, O.,
Least squares binary quantization of neural networks,
EDLCV20(2986-2996)
IEEE DOI 2008
Quantization (signal), Computational modeling, Optimization, Tensile stress, Neural networks, Computational efficiency, Approximation algorithms BibRef

Gope, D., Beu, J., Thakker, U., Mattina, M.,
Ternary MobileNets via Per-Layer Hybrid Filter Banks,
EDLCV20(3036-3046)
IEEE DOI 2008
Convolution, Quantization (signal), Computer architecture, Neural networks, Throughput, Hardware, Computational modeling BibRef

Wang, T., Wang, K., Cai, H., Lin, J., Liu, Z., Wang, H., Lin, Y., Han, S.,
APQ: Joint Search for Network Architecture, Pruning and Quantization Policy,
CVPR20(2075-2084)
IEEE DOI 2008
Quantization (signal), Optimization, Training, Hardware, Pipelines, Biological system modeling, Computer architecture BibRef

Yu, H.B.[Hai-Bao], Han, Q.[Qi], Li, J.B.[Jian-Bo], Shi, J.P.[Jian-Ping], Cheng, G.L.[Guang-Liang], Fan, B.[Bin],
Search What You Want: Barrier Penalty NAS for Mixed Precision Quantization,
ECCV20(IX:1-16).
Springer DOI 2011
BibRef

Marban, A.[Arturo], Becking, D.[Daniel], Wiedemann, S.[Simon], Samek, W.[Wojciech],
Learning Sparse Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T),
EDLCV20(3105-3113)
IEEE DOI 2008
Neural networks, Quantization (signal), Mathematical model, Computational modeling, Compounds, Entropy, Histograms BibRef

Langroudi, H.F.[Hamed F.], Karia, V.[Vedant], Gustafson, J.L.[John L.], Kudithipudi, D.[Dhireesha],
Adaptive Posit: Parameter aware numerical format for deep learning inference on the edge,
EDLCV20(3123-3131)
IEEE DOI 2008
Dynamic range, Neural networks, Quantization (signal), Computational modeling, Machine learning, Adaptation models, Numerical models BibRef

Mordido, G., van Keirsbilck, M., Keller, A.,
Monte Carlo Gradient Quantization,
EDLCV20(3087-3095)
IEEE DOI 2008
Training, Quantization (signal), Monte Carlo methods, Convergence, Neural networks, Heuristic algorithms, Image coding BibRef

Wiedemann, S., Mehari, T., Kepp, K., Samek, W.,
Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training,
EDLCV20(3096-3104)
IEEE DOI 2008
Quantization (signal), Training, Mathematical model, Standards, Neural networks, Convergence, Computational efficiency BibRef

Jiang, W., Wang, W., Liu, S.,
Structured Weight Unification and Encoding for Neural Network Compression and Acceleration,
EDLCV20(3068-3076)
IEEE DOI 2008
Quantization (signal), Computational modeling, Encoding, Image coding, Training, Acceleration, Predictive models BibRef

Yang, H., Gui, S., Zhu, Y., Liu, J.,
Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-Based Approach,
CVPR20(2175-2185)
IEEE DOI 2008
Quantization (signal), Optimization, Computational modeling, Tensile stress, Search problems, Neural networks, Image coding BibRef

Dong, Z., Yao, Z., Gholami, A., Mahoney, M., Keutzer, K.,
HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision,
ICCV19(293-302)
IEEE DOI 2004
image resolution, neural nets, quantisation (signal), neural networks, mixed-precision quantization, deep networks, Image resolution BibRef

Yang, J.[Jiwei], Shen, X.[Xu], Xing, J.[Jun], Tian, X.M.[Xin-Mei], Li, H.Q.A.[Hou-Qi-Ang], Deng, B.[Bing], Huang, J.Q.[Jian-Qiang], Hua, X.S.[Xian-Sheng],
Quantization Networks,
CVPR19(7300-7308).
IEEE DOI 2002
BibRef

Cao, S.J.[Shi-Jie], Ma, L.X.[Ling-Xiao], Xiao, W.C.[Wen-Cong], Zhang, C.[Chen], Liu, Y.X.[Yun-Xin], Zhang, L.T.[Lin-Tao], Nie, L.S.[Lan-Shun], Yang, Z.[Zhi],
SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization,
CVPR19(11208-11217).
IEEE DOI 2002
BibRef

Jung, S.[Sangil], Son, C.Y.[Chang-Yong], Lee, S.[Seohyung], Son, J.[Jinwoo], Han, J.J.[Jae-Joon], Kwak, Y.[Youngjun], Hwang, S.J.[Sung Ju], Choi, C.K.[Chang-Kyu],
Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss,
CVPR19(4345-4354).
IEEE DOI 2002
BibRef

Mitschke, N., Heizmann, M., Noffz, K., Wittmann, R.,
A Fixed-Point Quantization Technique for Convolutional Neural Networks Based on Weight Scaling,
ICIP19(3836-3840)
IEEE DOI 1910
CNNs, Fixed Point Quantization, Image Processing, Machine Vision, Deep Learning BibRef

Ajanthan, T., Dokania, P., Hartley, R., Torr, P.H.S.,
Proximal Mean-Field for Neural Network Quantization,
ICCV19(4870-4879)
IEEE DOI 2004
computational complexity, gradient methods, neural nets, optimisation, stochastic processes, proximal mean-field, Labeling BibRef

Gong, R., Liu, X., Jiang, S., Li, T., Hu, P., Lin, J., Yu, F., Yan, J.,
Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks,
ICCV19(4851-4860)
IEEE DOI 2004
backpropagation, convolutional neural nets, data compression, image coding, learning (artificial intelligence), Backpropagation BibRef

Choukroun, Y., Kravchik, E., Yang, F., Kisilev, P.,
Low-bit Quantization of Neural Networks for Efficient Inference,
CEFRL19(3009-3018)
IEEE DOI 2004
inference mechanisms, learning (artificial intelligence), mean square error methods, neural nets, quantisation (signal), MMSE BibRef

Hu, Y., Li, J., Long, X., Hu, S., Zhu, J., Wang, X., Gu, Q.,
Cluster Regularized Quantization for Deep Networks Compression,
ICIP19(914-918)
IEEE DOI 1910
deep neural networks, object classification, model compression, quantization BibRef

Manessi, F., Rozza, A., Bianco, S., Napoletano, P., Schettini, R.,
Automated Pruning for Deep Neural Network Compression,
ICPR18(657-664)
IEEE DOI 1812
Training, Neural networks, Quantization (signal), Task analysis, Feature extraction, Pipelines, Image coding BibRef

Zhuang, B., Shen, C., Tan, M., Liu, L., Reid, I.D.,
Towards Effective Low-Bitwidth Convolutional Neural Networks,
CVPR18(7920-7928)
IEEE DOI 1812
Quantization (signal), Training, Neural networks, Optimization, Zirconium, Hardware, Convolution BibRef

Faraone, J., Fraser, N., Blott, M., Leong, P.H.W.,
SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks,
CVPR18(4300-4309)
IEEE DOI 1812
Quantization (signal), Hardware, Symmetric matrices, Training, Complexity theory, Neural networks, Field programmable gate arrays BibRef

Frickenstein, A., Unger, C., Stechele, W.,
Resource-Aware Optimization of DNNs for Embedded Applications,
CRV19(17-24)
IEEE DOI 1908
Optimization, Hardware, Computational modeling, Quantization (signal), Training, Sensitivity, Autonomous vehicles, CNN BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Intrepretation, Explaination, Understanding of Convolutional Neural Networks .


Last update:Oct 16, 2021 at 11:54:21