JP7236873B2 - オートエンコーダ装置、データ処理システム、データ処理方法及びプログラム - Google Patents

オートエンコーダ装置、データ処理システム、データ処理方法及びプログラム Download PDF

Info

Publication number
JP7236873B2
JP7236873B2 JP2019022744A JP2019022744A JP7236873B2 JP 7236873 B2 JP7236873 B2 JP 7236873B2 JP 2019022744 A JP2019022744 A JP 2019022744A JP 2019022744 A JP2019022744 A JP 2019022744A JP 7236873 B2 JP7236873 B2 JP 7236873B2
Authority
JP
Japan
Prior art keywords
data
resolution
neural network
layer
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.)
Active
Application number
JP2019022744A
Other languages
English (en)
Japanese (ja)
Other versions
JP2019140680A5 (enExample
JP2019140680A (ja
Inventor
健 中西
新一 前田
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.)
Preferred Networks Inc
Original Assignee
Preferred Networks Inc
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
Application filed by Preferred Networks Inc filed Critical Preferred Networks Inc
Publication of JP2019140680A publication Critical patent/JP2019140680A/ja
Publication of JP2019140680A5 publication Critical patent/JP2019140680A5/ja
Application granted granted Critical
Publication of JP7236873B2 publication Critical patent/JP7236873B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/0495—Quantised networks; Sparse networks; Compressed networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • G06T9/002—Image coding using neural networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/56—Provisioning of proxy services
    • H04L67/565—Conversion or adaptation of application format or content
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/04—Protocols for data compression, e.g. ROHC

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Computer Security & Cryptography (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Compression Of Band Width Or Redundancy In Fax (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
JP2019022744A 2018-02-09 2019-02-12 オートエンコーダ装置、データ処理システム、データ処理方法及びプログラム Active JP7236873B2 (ja)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2018022349 2018-02-09
JP2018022349 2018-02-09

Publications (3)

Publication Number Publication Date
JP2019140680A JP2019140680A (ja) 2019-08-22
JP2019140680A5 JP2019140680A5 (enExample) 2022-04-25
JP7236873B2 true JP7236873B2 (ja) 2023-03-10

Family

ID=67541769

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2019022744A Active JP7236873B2 (ja) 2018-02-09 2019-02-12 オートエンコーダ装置、データ処理システム、データ処理方法及びプログラム

Country Status (2)

Country Link
US (1) US11902369B2 (enExample)
JP (1) JP7236873B2 (enExample)

Families Citing this family (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2797980C (en) 2010-05-12 2015-08-18 Irhythm Technologies, Inc. Device features and design elements for long-term adhesion
CA2898626C (en) 2013-01-24 2020-05-12 Irhythm Technologies, Inc. Physiological monitoring device
US11037330B2 (en) * 2017-04-08 2021-06-15 Intel Corporation Low rank matrix compression
JP7233875B2 (ja) * 2018-09-26 2023-03-07 株式会社Preferred Networks 作成方法、コンピュータ及びプログラム
KR102621118B1 (ko) * 2018-11-01 2024-01-04 삼성전자주식회사 영상 적응적 양자화 테이블을 이용한 영상의 부호화 장치 및 방법
US11588499B2 (en) * 2018-11-05 2023-02-21 Samsung Electronics Co., Ltd. Lossless compression of neural network weights
JP7328799B2 (ja) * 2019-06-12 2023-08-17 株式会社日立製作所 ストレージシステムおよび記憶制御方法
JP7205641B2 (ja) * 2019-09-24 2023-01-17 富士通株式会社 学習方法、学習プログラム、および学習装置
WO2021059348A1 (ja) * 2019-09-24 2021-04-01 富士通株式会社 学習方法、学習プログラム、および学習装置
WO2021075009A1 (ja) * 2019-10-16 2021-04-22 日本電信電話株式会社 学習装置、推定装置、学習方法及び学習プログラム
JP7355622B2 (ja) * 2019-11-29 2023-10-03 株式会社日立製作所 エンコーダを有するストレージシステム
CN113038134B (zh) * 2019-12-25 2023-08-01 武汉Tcl集团工业研究院有限公司 一种图片处理方法、智能终端及存储介质
CN113034625B (zh) * 2019-12-25 2023-06-20 武汉Tcl集团工业研究院有限公司 一种基于图片的无损压缩方法、智能终端及存储介质
CN111126589B (zh) * 2019-12-31 2022-05-20 昆仑芯(北京)科技有限公司 神经网络数据处理装置、方法和电子设备
EP4088454A4 (en) * 2020-01-10 2024-01-17 Nokia Technologies Oy CASCADE PREDICTION TRANSFORMATION APPROACH FOR MIXED HUMAN-MACHINE TARGETED VIDEO CODING
AU2021218704B2 (en) * 2020-02-12 2023-11-02 Irhythm Technologies, Inc. Non-invasive cardiac monitor and methods of using recorded cardiac data to infer a physiological characteristic of a patient
US12450500B2 (en) 2020-02-17 2025-10-21 Nec Corporation Communication system, transmission apparatus, reception apparatus, matrix generation apparatus, communication method, transmission method, reception method, matrix generation method and recording medium
US11356305B2 (en) * 2020-02-24 2022-06-07 Qualcomm Incorporated Method to convey the TX waveform distortion to the receiver
EP4133740A4 (en) * 2020-04-07 2024-04-17 Nokia Technologies Oy FEATURE DOMAIN RESIDUE FOR VIDEO CODING FOR MACHINES
US11823060B2 (en) * 2020-04-29 2023-11-21 HCL America, Inc. Method and system for performing deterministic data processing through artificial intelligence
US11955995B2 (en) * 2020-05-11 2024-04-09 Intel Corporation Apparatus and method for two-stage lossless data compression, and two-stage lossless data decompression
US20210406691A1 (en) * 2020-06-29 2021-12-30 Tencent America LLC Method and apparatus for multi-rate neural image compression with micro-structured masks
KR102510881B1 (ko) * 2020-07-01 2023-03-16 주식회사 딥브레인에이아이 신경망 기반의 특징점 학습 장치 및 방법
CN111898698B (zh) * 2020-08-10 2021-07-27 腾讯科技（深圳）有限公司 对象的处理方法及装置、存储介质和电子设备
CN117157645A (zh) * 2020-10-20 2023-12-01 诺基亚通信法国公司 上行链路ran中使用神经网络的预处理
US11915457B2 (en) * 2021-01-19 2024-02-27 Tencent America LLC Method and apparatus for adaptive neural image compression with rate control by meta-learning
JP7767028B2 (ja) * 2021-05-28 2025-11-11 株式会社日立製作所 データ処理システムおよびデータ処理方法
JP2022187683A (ja) 2021-06-08 2022-12-20 株式会社日立製作所 データ圧縮伸長システム、及びその方法
CN113720399B (zh) * 2021-11-02 2022-04-15 国网湖北省电力有限公司检修公司 特高压带电作业用绝缘吊带远程智能监测方法及装置
US11886955B2 (en) 2022-02-16 2024-01-30 Protopia AI, Inc. Self-supervised data obfuscation in foundation models
JP7691383B2 (ja) * 2022-02-18 2025-06-11 株式会社日立製作所 データ圧縮システム及びデータ圧縮方法
WO2023194651A1 (en) * 2022-04-07 2023-10-12 Nokia Technologies Oy A method, an apparatus and a computer program product for video encoding and video decoding
DE102023118393B4 (de) 2023-07-12 2025-01-23 Cariad Se Verfahren zum Betreiben eines faltenden neuronalen Netzwerks, Ein-Chip-System sowie Fahrzeug
WO2025127188A1 (ko) * 2023-12-13 2025-06-19 한국전자기술연구원 초경량 네트워크 모델 양자화 방법 및 이를 적용한 저전력 추론 가속기
WO2025187003A1 (ja) * 2024-03-07 2025-09-12 Ｎｔｔ株式会社 学習装置、通信システム及びプログラム
CN120074539B (zh) * 2025-04-29 2025-07-22 湖南科技大学 一种基于混合压缩算法的数据压缩方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005196040A (ja) 2004-01-09 2005-07-21 Japan Science & Technology Agency 歪みあり符号方法及び装置、歪みあり符号化プログラム及び記録媒体
JP2007503784A (ja) 2003-05-20 2007-02-22 アーエムテー アドバンスド マルチメディア テクノロジー アクティエボラーグ ハイブリッドビデオ圧縮法
JP2009273117A (ja) 2008-04-07 2009-11-19 Fujifilm Corp 画像処理システム、画像処理方法、およびプログラム
JP2013247683A (ja) 2012-05-24 2013-12-09 Fujitsu Ltd 画像圧縮方法及びその装置
WO2017196931A1 (en) 2016-05-10 2017-11-16 Google Llc Frequency based audio analysis using neural networks

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8261264B2 (en) * 2008-01-03 2012-09-04 Dell Products L.P. Accessing a network
JP2011526838A (ja) 2008-06-23 2011-10-20 マテリオン アドバンスト マテリアルズ テクノロジーズ アンド サービシーズ インコーポレイティド 無鉛スズ系はんだと適合する加工のための金−スズ−インジウムはんだ
WO2012109407A1 (en) 2011-02-09 2012-08-16 The Trustees Of Columbia University In The City Of New York Encoding and decoding machine with recurrent neural networks
US8582876B2 (en) * 2011-11-15 2013-11-12 Microsoft Corporation Hybrid codec for compound image compression
US9025910B2 (en) * 2012-12-13 2015-05-05 Futurewei Technologies, Inc. Image retargeting quality assessment
CN104579728B (zh) * 2013-10-17 2019-02-26 中兴通讯股份有限公司 网元设备配置和管理方法、装置及网元设备
CN109074512B (zh) 2016-02-05 2023-05-09 渊慧科技有限公司 使用神经网络压缩图像
US10831444B2 (en) * 2016-04-04 2020-11-10 Technion Research & Development Foundation Limited Quantized neural network training and inference
CN107786867A (zh) * 2016-08-26 2018-03-09 原相科技股份有限公司 基于深度学习架构的图像辨识方法及系统
JP6318211B2 (ja) 2016-10-03 2018-04-25 株式会社Ｐｒｅｆｅｒｒｅｄ Ｎｅｔｗｏｒｋｓ データ圧縮装置、データ再現装置、データ圧縮方法、データ再現方法及びデータ転送方法
BR112019027664B1 (pt) 2017-07-07 2023-12-19 Mitsubishi Electric Corporation Dispositivo e método de processamento de dados, e, meio de armazenamento

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007503784A (ja) 2003-05-20 2007-02-22 アーエムテー アドバンスド マルチメディア テクノロジー アクティエボラーグ ハイブリッドビデオ圧縮法
JP2005196040A (ja) 2004-01-09 2005-07-21 Japan Science & Technology Agency 歪みあり符号方法及び装置、歪みあり符号化プログラム及び記録媒体
JP2009273117A (ja) 2008-04-07 2009-11-19 Fujifilm Corp 画像処理システム、画像処理方法、およびプログラム
JP2013247683A (ja) 2012-05-24 2013-12-09 Fujitsu Ltd 画像圧縮方法及びその装置
WO2017196931A1 (en) 2016-05-10 2017-11-16 Google Llc Frequency based audio analysis using neural networks

Non-Patent Citations (8)

* Cited by examiner, † Cited by third party
Title
Adna Sento，Image Compression with Auto-encoder Algorithm using Deep Neural Network (DNN)，2016 Management and Innovation Technology International Conference (MITicon)，2016年，pp. MIT-99～MIT-103
Lucas Theis et al.，LOSSY IMAGE COMPRESSION WITH COMPRESSIVE AUTOENCODERS[online]，2017年03月01日，https://arxiv.org/pdf/1703.00395.pdf
小池 弘幸ほか，ＪＰＥＧ準拠のビットストリームに可逆変換可能な画像符号化方式，電子情報通信学会技術研究報告，2011年07月07日，第１１１巻，第１３３号，ｐｐ．２５～３０
山本 康平ほか，マイクロ波ビート信号の深層学習に基づく車種判別方式，電子情報通信学会技術研究報告，2016年，第１１６巻，第８９号，ｐｐ．１９～２４
梅本 可夏ほか，深層学習を用いた病理組織画像からの乳癌診断，電子情報通信学会技術研究報告，2017年05月18日，第１１７巻，第５０号，ｐｐ．１～６
石井 潤ほか，可変データビット幅を持つＤＮＮとそのアクセラレータアーキテクチャの検討，電子情報通信学会技術研究報告，2017年07月19日，第１１７巻，第１５４号，ｐｐ．８３～９０
神保 悟ほか，符号化パラメータ適応型ディープラーニングによるＨ．２６５／ＨＥＶＣ符号化雑音除去特性，第３２回画像符号化シンポジウム／第２２回映像メディア処理シンポジウム，2017年11月20日，ｐｐ．３４～３５
高田 遼ほか，スケーラブルなディープラーニング向けアクセラレータチップの設計と評価，電子情報通信学会技術研究報告，2016年，第１１６巻，第３３６号，ｐｐ．１～６

Also Published As

Publication number Publication date
US20190251418A1 (en) 2019-08-15
US11902369B2 (en) 2024-02-13
JP2019140680A (ja) 2019-08-22

Similar Documents

Publication Publication Date Title
JP7236873B2 (ja) オートエンコーダ装置、データ処理システム、データ処理方法及びプログラム
US11153566B1 (en) Variable bit rate generative compression method based on adversarial learning
US10733767B2 (en) Method and device for processing multi-channel feature map images
KR20220058628A (ko) 신경망 모델 압축
KR20200044652A (ko) 영상의 주관적 품질을 평가하는 방법 및 장치
CN113163203A (zh) 深度学习特征压缩和解压缩方法、系统及终端
JP7233875B2 (ja) 作成方法、コンピュータ及びプログラム
CN114386595A (zh) 一种基于超先验架构的sar图像压缩方法
US20230316048A1 (en) Multi-rate computer vision task neural networks in compression domain
US11900525B2 (en) Learned volumetric attribute compression using coordinate-based networks
CN119180874B (zh) 面向机器和人类视觉的图像编码、解码方法及压缩方法
Rai et al. An enhanced compression method for medical images using SPIHT encoder for fog computing
CN119110084A (zh) 一种基于最优传输映射的高压缩率图像压缩方法
US12335487B2 (en) Multi-rate of computer vision task neural networks in compression domain
US20230316588A1 (en) Online training-based encoder tuning with multi model selection in neural image compression
CN113949880A (zh) 一种极低码率人机协同图像编码训练方法及编解码方法
US20230306239A1 (en) Online training-based encoder tuning in neural image compression
TWI879536B (zh) 一種解碼、編碼方法、裝置及其設備
CN115866266A (zh) 一种应用于混合语境中的多码率深度图像压缩系统及方法
CN120692401B (zh) 基于频域增强与自适应优化的遥感图像压缩方法及装置
US12505581B2 (en) Online training computer vision task models in compression domain
CN118828001A (zh) 一种解码、编码方法、装置及其设备
US20230334718A1 (en) Online training computer vision task models in compression domain
KR20250087445A (ko) 암시적 신경망 비디오 표현에 기반하는 비디오 코딩방법 및 장치
CN121033191A (zh) 一种编码器端基于transformer的点云几何压缩方法及系统

Legal Events

Date Code Title Description
A80 Written request to apply exceptions to lack of novelty of invention

Free format text: JAPANESE INTERMEDIATE CODE: A80

Effective date: 20190301

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20220210

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20220414

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20221128

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20221223

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20230127

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20230203

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20230228

R150 Certificate of patent or registration of utility model

Ref document number: 7236873

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150