EP4062375A4 - Method and apparatus for quantization, adaptive block partitioning and codebook coding for neural network model compression - Google Patents

Method and apparatus for quantization, adaptive block partitioning and codebook coding for neural network model compression Download PDF

Info

Publication number
EP4062375A4
EP4062375A4 EP20890921.8A EP20890921A EP4062375A4 EP 4062375 A4 EP4062375 A4 EP 4062375A4 EP 20890921 A EP20890921 A EP 20890921A EP 4062375 A4 EP4062375 A4 EP 4062375A4
Authority
EP
European Patent Office
Prior art keywords
quantization
neural network
network model
block partitioning
model compression
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
EP20890921.8A
Other languages
German (de)
French (fr)
Other versions
EP4062375A1 (en
Inventor
Wei Wang
Wei Jiang
Shan Liu
Byeongdoo CHOI
Stephan Wenger
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent America LLC
Original Assignee
Tencent America LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US17/099,202 external-priority patent/US11245903B2/en
Application filed by Tencent America LLC filed Critical Tencent America LLC
Publication of EP4062375A1 publication Critical patent/EP4062375A1/en
Publication of EP4062375A4 publication Critical patent/EP4062375A4/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
    • H04N19/119—Adaptive subdivision aspects, e.g. subdivision of a picture into rectangular or non-rectangular coding blocks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
    • H04N19/124—Quantisation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
    • H04N19/129—Scanning of coding units, e.g. zig-zag scan of transform coefficients or flexible macroblock ordering [FMO]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/70—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
EP20890921.8A 2019-11-22 2020-11-19 Method and apparatus for quantization, adaptive block partitioning and codebook coding for neural network model compression Pending EP4062375A4 (en)

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
US201962939057P 2019-11-22 2019-11-22
US201962939054P 2019-11-22 2019-11-22
US201962939949P 2019-11-25 2019-11-25
US201962947236P 2019-12-12 2019-12-12
US17/099,202 US11245903B2 (en) 2019-11-22 2020-11-16 Method and apparatus for quantization, adaptive block partitioning and codebook coding for neural network model compression
PCT/US2020/061258 WO2021102125A1 (en) 2019-11-22 2020-11-19 Method and apparatus for quantization, adaptive block partitioning and codebook coding for neural network model compression

Publications (2)

Publication Number Publication Date
EP4062375A1 EP4062375A1 (en) 2022-09-28
EP4062375A4 true EP4062375A4 (en) 2022-12-28

Family

ID=75981074

Family Applications (1)

Application Number Title Priority Date Filing Date
EP20890921.8A Pending EP4062375A4 (en) 2019-11-22 2020-11-19 Method and apparatus for quantization, adaptive block partitioning and codebook coding for neural network model compression

Country Status (5)

Country Link
EP (1) EP4062375A4 (en)
JP (1) JP7337950B2 (en)
KR (1) KR20210136123A (en)
CN (1) CN113795869B (en)
WO (1) WO2021102125A1 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023051776A1 (en) * 2021-09-30 2023-04-06 咪咕文化科技有限公司 Encoding method and apparatus, decoding method and apparatus, device, and readable storage medium
TWI795135B (en) * 2021-12-22 2023-03-01 財團法人工業技術研究院 Quantization method for neural network model and deep learning accelerator
TWI819627B (en) * 2022-05-26 2023-10-21 緯創資通股份有限公司 Optimizing method and computing apparatus for deep learning network and computer readable storage medium

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190347550A1 (en) * 2018-05-14 2019-11-14 Samsung Electronics Co., Ltd. Method and apparatus with neural network parameter quantization

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9565437B2 (en) * 2013-04-08 2017-02-07 Qualcomm Incorporated Parameter set designs for video coding extensions
US10223635B2 (en) * 2015-01-22 2019-03-05 Qualcomm Incorporated Model compression and fine-tuning
US10515307B2 (en) * 2015-06-05 2019-12-24 Google Llc Compressed recurrent neural network models
US10748062B2 (en) * 2016-12-15 2020-08-18 WaveOne Inc. Deep learning based adaptive arithmetic coding and codelength regularization
EP3564864A4 (en) * 2016-12-30 2020-04-15 Shanghai Cambricon Information Technology Co., Ltd Devices for compression/decompression, system, chip, and electronic device
US11403528B2 (en) * 2018-05-31 2022-08-02 Kneron (Taiwan) Co., Ltd. Self-tuning incremental model compression solution in deep neural network with guaranteed accuracy performance
WO2020190772A1 (en) * 2019-03-15 2020-09-24 Futurewei Technologies, Inc. Neural network model compression and optimization
EP3716158A3 (en) * 2019-03-25 2020-11-25 Nokia Technologies Oy Compressing weight updates for decoder-side neural networks
CN110263913A (en) * 2019-05-23 2019-09-20 深圳先进技术研究院 A kind of deep neural network compression method and relevant device
CN110276451A (en) * 2019-06-28 2019-09-24 南京大学 One kind being based on the normalized deep neural network compression method of weight
CN110443359A (en) * 2019-07-03 2019-11-12 中国石油大学(华东) Neural network compression algorithm based on adaptive combined beta pruning-quantization
US11671110B2 (en) * 2019-11-22 2023-06-06 Tencent America LLC Method and apparatus for neural network model compression/decompression

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190347550A1 (en) * 2018-05-14 2019-11-14 Samsung Electronics Co., Ltd. Method and apparatus with neural network parameter quantization

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
AL-HAMI MO'TAZ ET AL: "Methodologies of Compressing a Stable Performance Convolutional Neural Networks in Image Classification", NEURAL PROCESSING LETTERS, KLUWER ACADEMIC PUBLISHERS, NORWELL, MA, US, vol. 51, no. 1, 20 July 2019 (2019-07-20), pages 105 - 127, XP037048818, ISSN: 1370-4621, [retrieved on 20190720], DOI: 10.1007/S11063-019-10076-Y *

Also Published As

Publication number Publication date
JP2022533307A (en) 2022-07-22
KR20210136123A (en) 2021-11-16
EP4062375A1 (en) 2022-09-28
JP7337950B2 (en) 2023-09-04
WO2021102125A1 (en) 2021-05-27
CN113795869A (en) 2021-12-14
CN113795869B (en) 2023-08-18

Similar Documents

Publication Publication Date Title
EP3770823A4 (en) Quantization parameter determination method for neural network, and related product
EP4062375A4 (en) Method and apparatus for quantization, adaptive block partitioning and codebook coding for neural network model compression
EP3822880A4 (en) Load prediction method and apparatus based on neural network
EP3614316A4 (en) Neural network model deployment method, prediction method, and apparatus
EP3912106A4 (en) Apparatus and a method for neural network compression
EP3685577A4 (en) Method and apparatus of neural network for video coding
EP4062320A4 (en) Method and apparatus for neural network model compression/decompression
EP3985509A4 (en) Neural network segmentation method, prediction method, and related apparatus
EP3926582A4 (en) Model generating apparatus, method, and program, and prediction apparatus
EP4062642A4 (en) Method and apparatus for motion prediction and video coding
EP3935578A4 (en) Neural network model apparatus and compressing method of neural network model
EP3925217A4 (en) Method and apparatus of the quantization matrix computation and representation for video coding
EP4030348A4 (en) Neural network training method, data processing method, and related apparatuses
EP4107628A4 (en) Method and apparatus for deep neural network based inter-frame prediction in video coding
EP4018656A4 (en) Linear model prediction method and coder
EP3836032A4 (en) Quantization method and apparatus for neural network model in device
EP3915253A4 (en) Method and apparatus for non-linear adaptive loop filtering in video coding
EP3882824A4 (en) Adaptive quantization method and apparatus, device and medium
EP3928517A4 (en) Method and apparatus for intra prediction using linear model
EP3905674A4 (en) Image coding method and device for carrying out mrl-based intra prediction
GB202108388D0 (en) Method and apparatus for adjusting quantization parameter for adaptive quantization
EP3779801A4 (en) Method for optimizing neural network parameter appropriate for hardware implementation, neural network operation method, and apparatus therefor
EP4011071A4 (en) Neural network model compression
EP4032265A4 (en) Sub-block motion prediction method, coding method, and encoder
MX2021014277A (en) Video coding method and apparatus using adaptive parameter set.

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20210916

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: DE

Ref legal event code: R079

Free format text: PREVIOUS MAIN CLASS: G06T0009000000

Ipc: H04N0019960000

A4 Supplementary search report drawn up and despatched

Effective date: 20221124

RIC1 Information provided on ipc code assigned before grant

Ipc: G06N 3/08 20060101ALI20221118BHEP

Ipc: G06N 3/04 20060101ALI20221118BHEP

Ipc: H04N 19/91 20140101ALI20221118BHEP

Ipc: H04N 19/119 20140101ALI20221118BHEP

Ipc: H04N 19/70 20140101ALI20221118BHEP

Ipc: H04N 19/96 20140101AFI20221118BHEP

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)