EP3698286A4 - Verfahren und system zur semantischen segmentierung mit einbeziehung eines neuronalen faltungsnetzes mit mehreren tasks - Google Patents

Verfahren und system zur semantischen segmentierung mit einbeziehung eines neuronalen faltungsnetzes mit mehreren tasks Download PDF

Info

Publication number
EP3698286A4
EP3698286A4 EP18913207.9A EP18913207A EP3698286A4 EP 3698286 A4 EP3698286 A4 EP 3698286A4 EP 18913207 A EP18913207 A EP 18913207A EP 3698286 A4 EP3698286 A4 EP 3698286A4
Authority
EP
European Patent Office
Prior art keywords
neuronal
inclusion
semantic segmentation
several tasks
folding network
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.)
Withdrawn
Application number
EP18913207.9A
Other languages
English (en)
French (fr)
Other versions
EP3698286A1 (de
Inventor
Bao RUXIAO
Xu XUN
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.)
Beijing Didi Infinity Technology and Development Co Ltd
Original Assignee
Beijing Didi Infinity Technology and Development Co Ltd
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 Beijing Didi Infinity Technology and Development Co Ltd filed Critical Beijing Didi Infinity Technology and Development Co Ltd
Publication of EP3698286A1 publication Critical patent/EP3698286A1/de
Publication of EP3698286A4 publication Critical patent/EP3698286A4/de
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • 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
    • G06N3/08—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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/096—Transfer learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G06T2207/30261—Obstacle

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)
EP18913207.9A 2018-12-31 2018-12-31 Verfahren und system zur semantischen segmentierung mit einbeziehung eines neuronalen faltungsnetzes mit mehreren tasks Withdrawn EP3698286A4 (de)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/US2018/068172 WO2020142077A1 (en) 2018-12-31 2018-12-31 Method and system for semantic segmentation involving multi-task convolutional neural network

Publications (2)

Publication Number Publication Date
EP3698286A1 EP3698286A1 (de) 2020-08-26
EP3698286A4 true EP3698286A4 (de) 2020-12-23

Family

ID=71407381

Family Applications (1)

Application Number Title Priority Date Filing Date
EP18913207.9A Withdrawn EP3698286A4 (de) 2018-12-31 2018-12-31 Verfahren und system zur semantischen segmentierung mit einbeziehung eines neuronalen faltungsnetzes mit mehreren tasks

Country Status (2)

Country Link
EP (1) EP3698286A4 (de)
WO (1) WO2020142077A1 (de)

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112489060B (zh) * 2020-12-07 2022-05-10 北京医准智能科技有限公司 一种用于肺炎病灶分割的系统及方法
CN113112454B (zh) * 2021-03-22 2024-03-19 西北工业大学 一种基于任务动态学习部分标记的医学图像分割方法
US12566941B2 (en) 2021-03-25 2026-03-03 GE Precision Healthcare LLC Extension of existing neural networks without affecting existing outputs
CN113348463B (zh) * 2021-04-26 2022-05-10 华为技术有限公司 一种信息处理方法及装置
CN115376176A (zh) * 2021-05-21 2022-11-22 阿里巴巴新加坡控股有限公司 图像处理方法及装置
CN113689438A (zh) * 2021-08-12 2021-11-23 华中农业大学 针对果粒边缘的葡萄果粒分割方法
CN114240945B (zh) * 2022-02-28 2022-05-10 科大天工智能装备技术（天津）有限公司 一种基于目标分割的桥梁钢索断裂检测方法及系统
CN114915786B (zh) * 2022-04-26 2023-07-28 哈尔滨工业大学（深圳） 一种面向物联网场景的非对称语义图像压缩方法
CN114972313B (zh) * 2022-06-22 2024-04-19 北京航空航天大学 图像分割网络预训练方法及装置
CN115273813B (zh) * 2022-07-08 2025-10-24 珠海亿智电子科技有限公司 哭声检测网络训练方法、装置、电子设备及存储介质
CN116543448B (zh) * 2022-07-14 2026-01-06 南京航空航天大学 一种被动式太赫兹图像的固定背景下人体自动跟踪方法
EP4577945A1 (de) * 2022-08-26 2025-07-02 INTEL Corporation Trainieren eines neuronalen netzwerks durch injektion von many-to-one-wissen
CN116109825A (zh) * 2023-02-03 2023-05-12 华为技术有限公司 语义分割模型训练方法、语义分割方法和装置
CN116342883B (zh) * 2023-03-30 2026-02-24 浙江大学 一种端到端无监督激光里程计与语义分割结合的方法
CN116452983B (zh) * 2023-06-12 2023-10-10 合肥工业大学 一种基于无人机航拍影像的国土地貌变化快速发现方法
CN117115650A (zh) * 2023-08-25 2023-11-24 齐鲁工业大学(山东省科学院) 一种基于编解码器技术的城市道路语义分割方法及系统
CN117574179B (zh) * 2024-01-16 2024-05-28 北京趋动智能科技有限公司 多任务学习模型构建方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11481585B2 (en) * 2016-05-20 2022-10-25 Canary Capital Llc Segmentation of data

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
CIPOLLA ROBERTO ET AL: "Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics", 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, IEEE, 18 June 2018 (2018-06-18), pages 7482 - 7491, XP033473668, DOI: 10.1109/CVPR.2018.00781 *
DUY-KIEN NGUYEN ET AL: "Multi-task Learning of Hierarchical Vision-Language Representation", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 3 December 2018 (2018-12-03), XP080988112 *
NEVEN DAVY ET AL: "Towards End-to-End Lane Detection: an Instance Segmentation Approach", 2018 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), IEEE, 26 June 2018 (2018-06-26), pages 286 - 291, XP033423446, DOI: 10.1109/IVS.2018.8500547 *
See also references of WO2020142077A1 *
XUE DI-XIU ET AL: "Fully convolutional networks with double-label for esophageal cancer image segmentation by self-transfer learning", PROCEEDINGS OF SPIE; [PROCEEDINGS OF SPIE ISSN 0277-786X VOLUME 10524], SPIE, US, vol. 10420, 21 July 2017 (2017-07-21), pages 104202D - 104202D, XP060092290, ISBN: 978-1-5106-1533-5, DOI: 10.1117/12.2282000 *

Also Published As

Publication number Publication date
WO2020142077A1 (en) 2020-07-09
EP3698286A1 (de) 2020-08-26

Similar Documents

Publication Publication Date Title
EP3698286A4 (de) Verfahren und system zur semantischen segmentierung mit einbeziehung eines neuronalen faltungsnetzes mit mehreren tasks
EP3738097C0 (de) System und verfahren zur schnellen bildsegmentierung auf der grundlage eines neuronalen netzes
EP3971789C0 (de) Vorrichtung und verfahren zur durchführung einer vorwärtsberechnung eines künstlichen neuronalen netzwerks
EP3607453A4 (de) Verfahren und vorrichtung für ausführungspipeline eines tiefenlernnetzes auf einer multiprozessorplattform
EP3545468C0 (de) Verfahren und system zum erstellen einer medizinischen bilddatenbank mittels eines konvolutionellen neuronalen netzwerk
EP3903307A4 (de) System und verfahren zur kommunikation mit einem benutzer mit sprachverarbeitung
EP3633557A4 (de) Vorrichtung und verfahren zur berechnung eines neuronalen netzes
EP3559345C0 (de) Verfahren zur herstellung eines beschichteten papiers, karton oder film und beschichtetes papier, karton oder film
EP3559100C0 (de) Lösungsmittel sowie verfahren zum lösen eines kunststoffs von einem feststoff innerhalb einer suspension
EP3729735A4 (de) Verfahren und vorrichtung zur konfiguration eines flex-ethernet-knotens
EP4191442A4 (de) Verfahren und system zur empfehlung eines cloud-computing-index
EP3729734A4 (de) Verfahren und vorrichtung zur konfiguration eines flex-ethernet-knotens
EP3678019A4 (de) Verfahren und vorrichtung zur verbesserung eines spiegelbildes
EP3872818A4 (de) Verfahren zur bereitstellung eines diagnosesystems mit halbüberwachtem lernen und diagnosesystem damit
EP3094765C0 (de) Verfahren zur herstellung einer chrombeschichtung und beschichteter gegenstand
EP3730269A4 (de) Verfahren zur herstellung einer gussform für brillengläser und verfahren zur herstellung eines brillenglases
EP3752051C0 (de) Verfahren zur erfassung und klassifizierung eines motorischen krampfanfalls
EP4078448C0 (de) Verfahren zum rechnergestützten lernen eines künstlichen neuronalen netzwerkes zur erkennung von strukturellen merkmalen von objekten
EP3535628A4 (de) Verfahren und system zur bereitstellung eines bearbeitungsverfahren zur herstellung einer funktion in einem teil
EP3989149C0 (de) Verfahren und vorrichtung zur ausführung eines intelligenten kontraktes
EP3784492C0 (de) Vorrichtung und verfahren zur herstellung eines dreidimensionalen objekts
EP3600835A4 (de) Vorrichtung und verfahren zur herstellung eines stereolithografischen objekts
EP3400096C0 (de) Verfahren und vorrichtung mit schnittstelle zur herstellung eines personalisierten kosmetischen produkts
EP3310549A4 (de) Verfahren und vorrichtung zur extrusion eines thermoplastischen handlaufs
EP3768917C0 (de) Strukturträgersystem und verfahren zur bereitstellung eines knotenabschnitts zur verwendung in einem strukturträgersystem

Legal Events

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

Free format text: STATUS: UNKNOWN

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: 20191011

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

AX Request for extension of the european patent

Extension state: BA ME

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.

A4 Supplementary search report drawn up and despatched

Effective date: 20201120

RIC1 Information provided on ipc code assigned before grant

Ipc: G06T 7/246 20170101ALI20201116BHEP

Ipc: G06N 3/04 20060101AFI20201116BHEP

Ipc: G06N 3/08 20060101ALI20201116BHEP

Ipc: G06T 7/11 20170101ALI20201116BHEP

Ipc: G06T 3/00 20060101ALI20201116BHEP

Ipc: G06T 1/20 20060101ALI20201116BHEP

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

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20211011

17Q First examination report despatched

Effective date: 20211022

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN WITHDRAWN

18W Application withdrawn

Effective date: 20220726