CN112132268A - 任务牵引的特征蒸馏深度神经网络学习训练方法及系统、可读存储介质 - Google Patents
任务牵引的特征蒸馏深度神经网络学习训练方法及系统、可读存储介质 Download PDFInfo
- Publication number
- CN112132268A CN112132268A CN202011030206.0A CN202011030206A CN112132268A CN 112132268 A CN112132268 A CN 112132268A CN 202011030206 A CN202011030206 A CN 202011030206A CN 112132268 A CN112132268 A CN 112132268A
- Authority
- CN
- China
- Prior art keywords
- task
- distillation
- neural network
- loss
- feature
- 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
Links
- 238000004821 distillation Methods 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 51
- 238000012549 training Methods 0.000 title claims abstract description 51
- 230000006870 function Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000011176 pooling Methods 0.000 claims description 5
- 238000013140 knowledge distillation Methods 0.000 abstract description 17
- 230000005540 biological transmission Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 14
- 230000006872 improvement Effects 0.000 description 14
- 238000002474 experimental method Methods 0.000 description 12
- 230000009466 transformation Effects 0.000 description 9
- 101100153586 Caenorhabditis elegans top-1 gene Proteins 0.000 description 6
- 101100370075 Mus musculus Top1 gene Proteins 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000002679 ablation Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
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
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (9)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011030206.0A CN112132268A (zh) | 2020-09-25 | 2020-09-25 | 任务牵引的特征蒸馏深度神经网络学习训练方法及系统、可读存储介质 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011030206.0A CN112132268A (zh) | 2020-09-25 | 2020-09-25 | 任务牵引的特征蒸馏深度神经网络学习训练方法及系统、可读存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112132268A true CN112132268A (zh) | 2020-12-25 |
Family
ID=73840509
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011030206.0A Pending CN112132268A (zh) | 2020-09-25 | 2020-09-25 | 任务牵引的特征蒸馏深度神经网络学习训练方法及系统、可读存储介质 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112132268A (zh) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112766463A (zh) * | 2021-01-25 | 2021-05-07 | 上海有个机器人有限公司 | 基于知识蒸馏技术优化神经网络模型的方法 |
CN113159073A (zh) * | 2021-04-23 | 2021-07-23 | 上海芯翌智能科技有限公司 | 知识蒸馏方法及装置、存储介质、终端 |
CN113505797A (zh) * | 2021-09-09 | 2021-10-15 | 深圳思谋信息科技有限公司 | 模型训练方法、装置、计算机设备和存储介质 |
CN113792871A (zh) * | 2021-08-04 | 2021-12-14 | 北京旷视科技有限公司 | 神经网络训练方法、目标识别方法、装置和电子设备 |
-
2020
- 2020-09-25 CN CN202011030206.0A patent/CN112132268A/zh active Pending
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112766463A (zh) * | 2021-01-25 | 2021-05-07 | 上海有个机器人有限公司 | 基于知识蒸馏技术优化神经网络模型的方法 |
CN113159073A (zh) * | 2021-04-23 | 2021-07-23 | 上海芯翌智能科技有限公司 | 知识蒸馏方法及装置、存储介质、终端 |
CN113159073B (zh) * | 2021-04-23 | 2022-11-18 | 上海芯翌智能科技有限公司 | 知识蒸馏方法及装置、存储介质、终端 |
CN113792871A (zh) * | 2021-08-04 | 2021-12-14 | 北京旷视科技有限公司 | 神经网络训练方法、目标识别方法、装置和电子设备 |
CN113505797A (zh) * | 2021-09-09 | 2021-10-15 | 深圳思谋信息科技有限公司 | 模型训练方法、装置、计算机设备和存储介质 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112132268A (zh) | 任务牵引的特征蒸馏深度神经网络学习训练方法及系统、可读存储介质 | |
CN111898095B (zh) | 深度迁移学习智能故障诊断方法、装置、存储介质和设备 | |
CN110378383B (zh) | 一种基于Keras框架和深度神经网络的图片分类方法 | |
DE112020003127T5 (de) | Erweiterung von dynamischem Verarbeitungselement-Array | |
WO2019091020A1 (zh) | 权重数据存储方法和基于该方法的神经网络处理器 | |
CN108921294A (zh) | 一种用于神经网络加速的渐进式块知识蒸馏方法 | |
CN107292352B (zh) | 基于卷积神经网络的图像分类方法和装置 | |
CN114049513A (zh) | 一种基于多学生讨论的知识蒸馏方法和系统 | |
CN106485259A (zh) | 一种基于高约束高分散主成分分析网络的图像分类方法 | |
CN110909801A (zh) | 基于卷积神经网络的数据分类方法、系统、介质及设备 | |
US11899744B2 (en) | Apparatus and method of performing matrix multiplication operation of neural network | |
CN115100238A (zh) | 基于知识蒸馏的轻量化单目标跟踪器训练方法 | |
CN114328834A (zh) | 一种模型蒸馏方法、系统以及文本检索方法 | |
CN110837570A (zh) | 对图像数据进行无偏见分类的方法 | |
Zhou et al. | Online filter clustering and pruning for efficient convnets | |
CN109784159A (zh) | 场景图像的处理方法、装置及系统 | |
CN104794455A (zh) | 一种东巴象形文字识别方法 | |
Li et al. | Incremental learning of single-stage detectors with mining memory neurons | |
Abdurrahman et al. | Generative adversarial network implementation for batik motif synthesis | |
CN115424288A (zh) | 一种基于多维度关系建模的视觉Transformer自监督学习方法及系统 | |
Halkias et al. | Sparse penalty in deep belief networks: using the mixed norm constraint | |
Goncharov et al. | Architecture and basic principles of the multifunctional platform for plant disease detection | |
CN112884160B (zh) | 一种元学习方法及相关装置 | |
Agustiono et al. | A modification of convolutional neural network layer to increase images classification accuracy | |
WO2021059527A1 (ja) | 学習装置、学習方法、及び、記録媒体 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB03 | Change of inventor or designer information |
Inventor after: Zhang Linfeng Inventor before: Ma Kaisheng Inventor before: Zhang Linfeng |
|
CB03 | Change of inventor or designer information | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20240529 Address after: 710077 5th floor, B3, phase II, software new town, tianguba Road, Yanta District, Xi'an City, Shaanxi Province Applicant after: Cross Information Core Technology Research Institute (Xi'an) Co.,Ltd. Country or region after: China Applicant after: TSINGHUA University Address before: 710077 11th floor, building B2, yunhuigu 156, software new town, Tiangu 8th Road, high tech Zone, Xi'an City, Shaanxi Province Applicant before: Cross Information Core Technology Research Institute (Xi'an) Co.,Ltd. Country or region before: China |