JP6776331B2 - 未知クラスの検出および未知クラスのための分類器の初期化 - Google Patents

未知クラスの検出および未知クラスのための分類器の初期化 Download PDF

Info

Publication number
JP6776331B2
JP6776331B2 JP2018505589A JP2018505589A JP6776331B2 JP 6776331 B2 JP6776331 B2 JP 6776331B2 JP 2018505589 A JP2018505589 A JP 2018505589A JP 2018505589 A JP2018505589 A JP 2018505589A JP 6776331 B2 JP6776331 B2 JP 6776331B2
Authority
JP
Japan
Prior art keywords
classifier
classes
data
class
unknown
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
JP2018505589A
Other languages
English (en)
Japanese (ja)
Other versions
JP2018528525A (ja
JP2018528525A5 (enExample
Inventor
マジュムダル、ソムデブ
リン、デシュ
トワル、レーガン・ブライス
サラ、アンソニー
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.)
Qualcomm Inc
Original Assignee
Qualcomm 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 Qualcomm Inc filed Critical Qualcomm Inc
Publication of JP2018528525A publication Critical patent/JP2018528525A/ja
Publication of JP2018528525A5 publication Critical patent/JP2018528525A5/ja
Application granted granted Critical
Publication of JP6776331B2 publication Critical patent/JP6776331B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield 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
    • G06N3/08—Learning methods
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Image Analysis (AREA)
JP2018505589A 2015-08-04 2016-07-20 未知クラスの検出および未知クラスのための分類器の初期化 Active JP6776331B2 (ja)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US201562201090P 2015-08-04 2015-08-04
US62/201,090 2015-08-04
US14/849,518 2015-09-09
US14/849,518 US20170039469A1 (en) 2015-08-04 2015-09-09 Detection of unknown classes and initialization of classifiers for unknown classes
PCT/US2016/043146 WO2017023551A2 (en) 2015-08-04 2016-07-20 Detection of unknown classes and initialization of classifiers for unknown classes

Publications (3)

Publication Number Publication Date
JP2018528525A JP2018528525A (ja) 2018-09-27
JP2018528525A5 JP2018528525A5 (enExample) 2019-08-08
JP6776331B2 true JP6776331B2 (ja) 2020-10-28

Family

ID=56555818

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2018505589A Active JP6776331B2 (ja) 2015-08-04 2016-07-20 未知クラスの検出および未知クラスのための分類器の初期化

Country Status (6)

Country Link
US (1) US20170039469A1 (enExample)
EP (1) EP3332362B1 (enExample)
JP (1) JP6776331B2 (enExample)
KR (1) KR102595399B1 (enExample)
CN (1) CN107924491A (enExample)
WO (1) WO2017023551A2 (enExample)

Families Citing this family (47)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170178346A1 (en) * 2015-12-16 2017-06-22 High School Cube, Llc Neural network architecture for analyzing video data
US11188823B2 (en) * 2016-05-31 2021-11-30 Microsoft Technology Licensing, Llc Training a neural network using another neural network
DE102016008218A1 (de) * 2016-07-06 2018-01-11 Audi Ag Verfahren zum verbesserten Erkennen von Objekten durch ein Fahrerassistenzsystem
US11095590B2 (en) * 2016-09-28 2021-08-17 International Business Machines Corporation System and method for enhanced chatflow application
US10719770B2 (en) 2016-09-28 2020-07-21 International Business Machines Corporation System and method for enhanced chatflow application
US10417530B2 (en) 2016-09-30 2019-09-17 Cylance Inc. Centroid for improving machine learning classification and info retrieval
US10621210B2 (en) * 2016-11-27 2020-04-14 Amazon Technologies, Inc. Recognizing unknown data objects
US10747994B2 (en) * 2016-12-28 2020-08-18 Captricity, Inc. Identifying versions of a form
CN108269224B (zh) * 2017-01-04 2022-04-01 意法半导体股份有限公司 可重新配置的互连
CN110651276A (zh) 2017-03-17 2020-01-03 纽拉拉股份有限公司 标注和标记用于深度神经网络和神经网络应用的数据流的在线增量实时学习
US11531876B2 (en) * 2017-03-29 2022-12-20 University Of Florida Research Foundation, Incorporated Deep learning for characterizing unseen categories
US10242486B2 (en) * 2017-04-17 2019-03-26 Intel Corporation Augmented reality and virtual reality feedback enhancement system, apparatus and method
US11829848B2 (en) 2017-05-09 2023-11-28 Microsoft Technology Licensing, Llc Adding negative classes for training classifier
US20180330238A1 (en) 2017-05-09 2018-11-15 Neurala, Inc. Systems and methods to enable continual, memory-bounded learning in artificial intelligence and deep learning continuously operating applications across networked compute edges
US20180336439A1 (en) * 2017-05-18 2018-11-22 Intel Corporation Novelty detection using discriminator of generative adversarial network
JP6967201B2 (ja) * 2017-09-26 2021-11-17 株式会社アイシン 情報処理装置
CN113536019B (zh) 2017-09-27 2025-01-07 深圳市商汤科技有限公司 一种图像检索方法、装置及计算机可读存储介质
KR102018788B1 (ko) * 2017-12-15 2019-11-04 서울시립대학교 산학협력단 이미지 분류 시스템 및 방법
US10528800B2 (en) * 2018-01-10 2020-01-07 International Business Machines Corporation Automated facial recognition detection
JP6933164B2 (ja) * 2018-03-08 2021-09-08 株式会社Ｊｖｃケンウッド 学習用データ作成装置、学習用モデル作成システム、学習用データ作成方法、及びプログラム
WO2019226670A1 (en) 2018-05-21 2019-11-28 Neurala, Inc. Systems and methods for deep neural networks on device learning (online and offline) with and without supervision
US20200057918A1 (en) * 2018-08-17 2020-02-20 Perfect Price, Inc. Systems and methods for training artificial intelligence to predict utilization of resources
CN109635863B (zh) * 2018-12-06 2023-08-25 邵凌霜 智能判断用户乘车的方法和装置
US11687761B2 (en) * 2018-12-11 2023-06-27 Amazon Technologies, Inc. Improper neural network input detection and handling
JP7492226B2 (ja) * 2018-12-13 2024-05-29 成典 田中 移動物追跡装置
US10621473B1 (en) * 2019-01-30 2020-04-14 StradVision, Inc. Method for providing object detecting system capable of updating types of detectable classes in real-time by using continual learning and devices using the same
US11790275B2 (en) * 2019-04-18 2023-10-17 Teledyne Scientific & Imaging, Llc Adaptive continuous machine learning by uncertainty tracking
CN110047506B (zh) * 2019-04-19 2021-08-20 杭州电子科技大学 一种基于卷积神经网络和多核学习svm的关键音频检测方法
CN110188197B (zh) * 2019-05-13 2021-09-28 北京一览群智数据科技有限责任公司 一种用于标注平台的主动学习方法及装置
US20220245728A1 (en) * 2019-06-24 2022-08-04 Fergal MCGUINNESS System for evaluating and replicating acturial calculation patterns using neural imaging and method thereof
EP3864577B1 (en) * 2019-06-25 2023-12-13 Owkin, Inc. Systems and methods for image preprocessing
JP7486079B2 (ja) * 2019-06-25 2024-05-17 パナソニックＩｐマネジメント株式会社 情報処理方法、及び、情報処理システム
US11586982B2 (en) 2019-09-18 2023-02-21 Samsung Electronics Co., Ltd. Electronic and atomic structure computation utilizing machine learning
US11537898B2 (en) 2019-10-02 2022-12-27 Samsung Electronics Co., Ltd. Generative structure-property inverse computational co-design of materials
JP7270127B2 (ja) 2019-10-07 2023-05-10 パナソニックＩｐマネジメント株式会社 分類システム、分類方法、及びプログラム
JP7563387B2 (ja) * 2019-11-19 2024-10-08 株式会社レゾナック 機械学習装置、方法、プログラム、およびシステム
KR20220160536A (ko) * 2020-03-31 2022-12-06 도레이 카부시키가이샤 데이터 분류 장치, 데이터 분류 방법, 및 데이터 분류 프로그램
JP7354063B2 (ja) * 2020-05-14 2023-10-02 株式会社東芝 分類システム、プログラム及び学習システム
JP7101920B2 (ja) * 2020-05-15 2022-07-15 三菱電機株式会社 攻撃検知システム、攻撃検知方法および攻撃検知プログラム
DE102020209130B4 (de) * 2020-07-21 2023-05-11 Magna Exteriors Gmbh Verkleidungsanordnung zur Verkleidung eines Karosserieelements für ein Kraftfahrzeug, sowie ein Verfahren zur zwangsgesteuerten Verlagerung einer Luftleitvorrichtung einer Verkleidungsanordnung
JP7552287B2 (ja) * 2020-11-25 2024-09-18 セイコーエプソン株式会社 物体検出方法、物体検出装置、及び、コンピュータープログラム
CN116997896A (zh) * 2021-03-23 2023-11-03 高通股份有限公司 用于恢复嵌入式系统上的顺序传感器数据的分类的状态变化检测
US12022358B2 (en) * 2021-04-13 2024-06-25 Qualcomm Incorporated Self-supervised passive positioning using wireless data
US11803575B2 (en) * 2022-01-24 2023-10-31 My Job Matcher, Inc. Apparatus, system, and method for classifying and neutralizing bias in an application
CN114241526B (zh) * 2022-02-28 2022-05-17 南京甄视智能科技有限公司 分类模型、训练方法、分类方法、电子设备及存储介质
JP2023132261A (ja) * 2022-03-10 2023-09-22 株式会社日本総合研究所 情報処理方法、情報処理プログラム、及び情報処理装置、並びに学習済みモデル
US12368503B2 (en) 2023-12-27 2025-07-22 Quantum Generative Materials Llc Intent-based satellite transmit management based on preexisting historical location and machine learning

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009090584A2 (en) * 2008-01-18 2009-07-23 Koninklijke Philips Electronics N.V. Method and system for activity recognition and its application in fall detection
US8386401B2 (en) * 2008-09-10 2013-02-26 Digital Infuzion, Inc. Machine learning methods and systems for identifying patterns in data using a plurality of learning machines wherein the learning machine that optimizes a performance function is selected
US9165051B2 (en) * 2010-08-24 2015-10-20 Board Of Trustees Of The University Of Illinois Systems and methods for detecting a novel data class
JP5828552B2 (ja) * 2011-12-22 2015-12-09 本田技研工業株式会社 物体分類装置、物体分類方法、物体認識装置及び物体認識方法

Also Published As

Publication number Publication date
EP3332362A2 (en) 2018-06-13
EP3332362B1 (en) 2024-10-30
JP2018528525A (ja) 2018-09-27
WO2017023551A3 (en) 2017-04-13
US20170039469A1 (en) 2017-02-09
KR20180037192A (ko) 2018-04-11
BR112018002248A2 (pt) 2018-09-18
WO2017023551A2 (en) 2017-02-09
CN107924491A (zh) 2018-04-17
KR102595399B1 (ko) 2023-10-27

Similar Documents

Publication Publication Date Title
JP6776331B2 (ja) 未知クラスの検出および未知クラスのための分類器の初期化
JP6869948B2 (ja) ニューラルネットワークにおける転移学習
JP7037478B2 (ja) 分類のための強制的なスパース性
JP6862426B2 (ja) トレーニングされた機械学習モデルのパフォーマンスを改善するための方法
JP6859332B2 (ja) 選択的バックプロパゲーション
US11334789B2 (en) Feature selection for retraining classifiers
US10275719B2 (en) Hyper-parameter selection for deep convolutional networks
US20160283864A1 (en) Sequential image sampling and storage of fine-tuned features
JP2018528521A (ja) メディア分類
JP2018520404A (ja) ニューラルネットワークのためのトレーニング基準としてのフィルタ特異性
JP2018518740A (ja) バイアス項を介して深層ニューラルネットワーク中にトップダウン情報を組み込むこと
JP2018526723A (ja) 画像中のオブジェクト検出のためのコンテキストベースの事前分布

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20190628

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20190628

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20200526

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20200825

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: 20200908

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20201007

R150 Certificate of patent or registration of utility model

Ref document number: 6776331

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250