HK1249627A1 - 用於卷積神經網絡的超像素方法 - Google Patents

用於卷積神經網絡的超像素方法

Info

Publication number
HK1249627A1
HK1249627A1 HK18109158.9A HK18109158A HK1249627A1 HK 1249627 A1 HK1249627 A1 HK 1249627A1 HK 18109158 A HK18109158 A HK 18109158A HK 1249627 A1 HK1249627 A1 HK 1249627A1
Authority
HK
Hong Kong
Prior art keywords
convolutional neural
neural networks
superpixel methods
superpixel
methods
Prior art date
Application number
HK18109158.9A
Other languages
English (en)
Inventor
雷吉納爾德‧克利福德‧揚
喬納森‧羅斯
Original Assignee
谷歌有限責任公司
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 谷歌有限責任公司 filed Critical 谷歌有限責任公司
Publication of HK1249627A1 publication Critical patent/HK1249627A1/zh

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
    • G06N3/04—Architecture, e.g. interconnection topology
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • 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
    • 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
    • G06N3/048—Activation functions
    • 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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • 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
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Neurology (AREA)
  • Image Analysis (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Complex Calculations (AREA)
  • Separation By Low-Temperature Treatments (AREA)
HK18109158.9A 2016-07-13 2018-07-16 用於卷積神經網絡的超像素方法 HK1249627A1 (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US15/209,658 US10706348B2 (en) 2016-07-13 2016-07-13 Superpixel methods for convolutional neural networks

Publications (1)

Publication Number Publication Date
HK1249627A1 true HK1249627A1 (zh) 2018-11-02

Family

ID=59558449

Family Applications (1)

Application Number Title Priority Date Filing Date
HK18109158.9A HK1249627A1 (zh) 2016-07-13 2018-07-16 用於卷積神經網絡的超像素方法

Country Status (13)

Country Link
US (4) US10706348B2 (zh)
EP (2) EP3469520B1 (zh)
JP (3) JP2019527420A (zh)
KR (3) KR20240058211A (zh)
CN (2) CN112801279A (zh)
AU (3) AU2017295714B2 (zh)
BR (1) BR112019000541B1 (zh)
CA (1) CA3030428C (zh)
DE (2) DE202017104127U1 (zh)
GB (1) GB2553900A (zh)
HK (1) HK1249627A1 (zh)
SG (1) SG11201900240WA (zh)
WO (1) WO2018013809A1 (zh)

Families Citing this family (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10896366B2 (en) * 2016-05-17 2021-01-19 Huawei Technologies Co., Ltd. Reduction of parameters in fully connected layers of neural networks by low rank factorizations
US10706348B2 (en) * 2016-07-13 2020-07-07 Google Llc Superpixel methods for convolutional neural networks
US10733505B2 (en) 2016-11-10 2020-08-04 Google Llc Performing kernel striding in hardware
US10540590B2 (en) * 2016-12-29 2020-01-21 Zhejiang Gongshang University Method for generating spatial-temporally consistent depth map sequences based on convolution neural networks
US10339443B1 (en) * 2017-02-24 2019-07-02 Gopro, Inc. Systems and methods for processing convolutional neural network operations using textures
US10896367B2 (en) * 2017-03-07 2021-01-19 Google Llc Depth concatenation using a matrix computation unit
US10776694B2 (en) * 2017-05-16 2020-09-15 Samsung Electronics Co., Ltd. Optimized neural network input stride method and apparatus
US11227108B2 (en) * 2017-09-11 2022-01-18 Nec Corporation Convolutional neural network architecture with adaptive filters
US11010666B1 (en) * 2017-10-24 2021-05-18 Tunnel Technologies Inc. Systems and methods for generation and use of tensor networks
JP6947300B2 (ja) * 2017-10-25 2021-10-13 日本電気株式会社 情報処理装置、情報処理方法、及びプログラム
CN107729994B (zh) * 2017-11-28 2020-05-26 南京地平线机器人技术有限公司 执行卷积神经网络中的卷积层的运算的方法和装置
CN107832842B (zh) * 2017-11-28 2020-05-22 南京地平线机器人技术有限公司 针对折叠特征数据执行卷积运算的方法和装置
US20210241068A1 (en) * 2018-04-30 2021-08-05 Hewlett Packard Enterprise Development Lp Convolutional neural network
US11847553B2 (en) * 2018-06-14 2023-12-19 International Business Machines Corporation Parallel computational architecture with reconfigurable core-level and vector-level parallelism
KR102637105B1 (ko) * 2018-07-13 2024-02-15 삼성전자주식회사 영상 데이터를 처리하는 방법 및 장치
JP7315317B2 (ja) 2018-11-09 2023-07-26 株式会社Preferred Networks プロセッサおよびプロセッサのデータ転送方法
US11200438B2 (en) * 2018-12-07 2021-12-14 Dus Operating Inc. Sequential training method for heterogeneous convolutional neural network
CN111542839B (zh) * 2018-12-13 2023-04-04 深圳鲲云信息科技有限公司 一种反卷积神经网络的硬件加速方法、装置和电子设备
US10325371B1 (en) * 2019-01-22 2019-06-18 StradVision, Inc. Method and device for segmenting image to be used for surveillance using weighted convolution filters for respective grid cells by converting modes according to classes of areas to satisfy level 4 of autonomous vehicle, and testing method and testing device using the same
CN109886399B (zh) * 2019-02-13 2021-03-23 上海燧原智能科技有限公司 一种张量处理装置及方法
JP7279446B2 (ja) * 2019-03-20 2023-05-23 富士通株式会社 学習プログラム、学習方法、及び学習装置
US20200356836A1 (en) * 2019-05-07 2020-11-12 Apple Inc. Fast deep learning fully-connected column-major implementation
US11487998B2 (en) * 2019-06-17 2022-11-01 Qualcomm Incorporated Depth-first convolution in deep neural networks
CN112308197B (zh) * 2019-07-26 2024-04-09 杭州海康威视数字技术股份有限公司 一种卷积神经网络的压缩方法、装置及电子设备
US11494608B2 (en) * 2019-08-14 2022-11-08 Intel Corporation Methods and apparatus to tile walk a tensor for convolution operations
WO2021061135A1 (en) * 2019-09-26 2021-04-01 Hewlett-Packard Development Company, L.P. Labeling pixels having defects
KR20210084123A (ko) * 2019-12-27 2021-07-07 삼성전자주식회사 전자 장치 및 그 제어 방법
US11252004B2 (en) * 2020-03-30 2022-02-15 Huawei Technologies Co., Ltd. Multiple access wireless communications using a non-gaussian manifold
US11886983B2 (en) * 2020-08-25 2024-01-30 Microsoft Technology Licensing, Llc Reducing hardware resource utilization for residual neural networks
TWI768517B (zh) * 2020-10-21 2022-06-21 國立政治大學 影像品質提昇方法及使用該方法的影像處理裝置
WO2023141937A1 (en) * 2022-01-28 2023-08-03 Nvidia Corporation Tensor modification based on processing resources

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9292787B2 (en) 2012-08-29 2016-03-22 Microsoft Technology Licensing, Llc Computer-implemented deep tensor neural network
US9191256B2 (en) * 2012-12-03 2015-11-17 Digital PowerRadio, LLC Systems and methods for advanced iterative decoding and channel estimation of concatenated coding systems
US9811775B2 (en) 2012-12-24 2017-11-07 Google Inc. Parallelizing neural networks during training
US9445713B2 (en) * 2013-09-05 2016-09-20 Cellscope, Inc. Apparatuses and methods for mobile imaging and analysis
KR20150108701A (ko) * 2014-03-18 2015-09-30 삼성전자주식회사 의료 영상 내 해부학적 요소 시각화 시스템 및 방법
US20170032285A1 (en) * 2014-04-09 2017-02-02 Entrupy Inc. Authenticating physical objects using machine learning from microscopic variations
US9536293B2 (en) 2014-07-30 2017-01-03 Adobe Systems Incorporated Image assessment using deep convolutional neural networks
US9536167B2 (en) * 2014-12-10 2017-01-03 Ricoh Co., Ltd. Realogram scene analysis of images: multiples for scene analysis
US10223635B2 (en) * 2015-01-22 2019-03-05 Qualcomm Incorporated Model compression and fine-tuning
CN104915322B (zh) 2015-06-09 2018-05-01 中国人民解放军国防科学技术大学 一种卷积神经网络硬件加速方法
JP2017068608A (ja) * 2015-09-30 2017-04-06 株式会社東芝 演算装置、方法及びプログラム
US9904874B2 (en) 2015-11-05 2018-02-27 Microsoft Technology Licensing, Llc Hardware-efficient deep convolutional neural networks
JP6116650B1 (ja) * 2015-11-17 2017-04-19 エヌ・ティ・ティ・コムウェア株式会社 学習支援システム、学習支援方法、学習支援装置、および学習支援プログラム
WO2017100903A1 (en) * 2015-12-14 2017-06-22 Motion Metrics International Corp. Method and apparatus for identifying fragmented material portions within an image
US10706348B2 (en) * 2016-07-13 2020-07-07 Google Llc Superpixel methods for convolutional neural networks
US10223788B2 (en) * 2016-08-31 2019-03-05 International Business Machines Corporation Skin lesion segmentation using deep convolution networks guided by local unsupervised learning
US10540590B2 (en) * 2016-12-29 2020-01-21 Zhejiang Gongshang University Method for generating spatial-temporally consistent depth map sequences based on convolution neural networks
CN108664981B (zh) * 2017-03-30 2021-10-26 北京航空航天大学 显著图像提取方法及装置
US10726599B2 (en) * 2017-08-17 2020-07-28 Adobe Inc. Realistic augmentation of images and videos with graphics

Also Published As

Publication number Publication date
CN107622302B (zh) 2021-03-19
EP4357979A2 (en) 2024-04-24
AU2020220126A1 (en) 2020-09-17
AU2022200600A1 (en) 2022-02-24
CN112801279A (zh) 2021-05-14
DE202017104127U1 (de) 2017-10-20
KR20240058211A (ko) 2024-05-03
US9940573B2 (en) 2018-04-10
AU2022200600B2 (en) 2023-11-16
GB2553900A (en) 2018-03-21
JP2019527420A (ja) 2019-09-26
DE102017115519A1 (de) 2018-01-18
JP7244598B2 (ja) 2023-03-22
KR20210158436A (ko) 2021-12-30
CA3030428C (en) 2021-01-12
EP3469520A1 (en) 2019-04-17
EP3469520B1 (en) 2024-01-03
JP2023078247A (ja) 2023-06-06
AU2017295714B2 (en) 2020-06-04
US20180018554A1 (en) 2018-01-18
US20210125029A1 (en) 2021-04-29
CA3030428A1 (en) 2018-01-18
US10706348B2 (en) 2020-07-07
SG11201900240WA (en) 2019-02-27
AU2017295714A1 (en) 2019-01-24
US20180018556A1 (en) 2018-01-18
CN107622302A (zh) 2018-01-23
WO2018013809A1 (en) 2018-01-18
KR20190028501A (ko) 2019-03-18
KR102344473B1 (ko) 2021-12-27
JP2022008571A (ja) 2022-01-13
AU2020220126B2 (en) 2021-11-04
BR112019000541A2 (pt) 2019-04-24
KR102662349B1 (ko) 2024-04-29
US20200125922A1 (en) 2020-04-23
US10810483B2 (en) 2020-10-20
BR112019000541B1 (pt) 2024-01-09
GB201711260D0 (en) 2017-08-30

Similar Documents

Publication Publication Date Title
HK1249627A1 (zh) 用於卷積神經網絡的超像素方法
IL281321A (en) Efficient data layouts for convolutional neural networks
IL271119A (en) Deep and complex neural networks for variant classification
GB2582519B (en) Convolutional neural network hardware
PL3459017T3 (pl) Progresywne sieci neuronowe
GB201610748D0 (en) Improved diffrentation method
ZA201905869B (en) Octree-based convolutional neural network
GB201607521D0 (en) Method
GB201602394D0 (en) Method
GB201601773D0 (en) Method
GB201603367D0 (en) Method
EP3554530C0 (en) ANTIBACTERIAL PROCESS
GB201602927D0 (en) Method
GB201601120D0 (en) Eye-testing method
GB2563846B (en) Improved manufacturing method
GB201614216D0 (en) Communication method
GB201603663D0 (en) Method
GB201603395D0 (en) Method
GB201603387D0 (en) Method
GB201603192D0 (en) Method
GB201602413D0 (en) Method
GB201601155D0 (en) Method
GB201601153D0 (en) Method
GB201601098D0 (en) Method
GB201601088D0 (en) Method