CN115272881A - 动态关系蒸馏的长尾遥感图像目标识别方法 - Google Patents
动态关系蒸馏的长尾遥感图像目标识别方法 Download PDFInfo
- Publication number
- CN115272881A CN115272881A CN202210920420.6A CN202210920420A CN115272881A CN 115272881 A CN115272881 A CN 115272881A CN 202210920420 A CN202210920420 A CN 202210920420A CN 115272881 A CN115272881 A CN 115272881A
- Authority
- CN
- China
- Prior art keywords
- network
- teacher
- feature
- student
- tail
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004821 distillation Methods 0.000 title claims abstract description 13
- 238000009826 distribution Methods 0.000 claims abstract description 23
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 46
- WDLRUFUQRNWCPK-UHFFFAOYSA-N Tetraxetan Chemical group OC(=O)CN1CCN(CC(O)=O)CCN(CC(O)=O)CCN(CC(O)=O)CC1 WDLRUFUQRNWCPK-UHFFFAOYSA-N 0.000 claims description 8
- 238000013145 classification model Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000010365 information processing Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 5
- 238000012952 Resampling Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013140 knowledge distillation Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (1)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210920420.6A CN115272881B (zh) | 2022-08-02 | 2022-08-02 | 动态关系蒸馏的长尾遥感图像目标识别方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210920420.6A CN115272881B (zh) | 2022-08-02 | 2022-08-02 | 动态关系蒸馏的长尾遥感图像目标识别方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115272881A true CN115272881A (zh) | 2022-11-01 |
CN115272881B CN115272881B (zh) | 2023-03-21 |
Family
ID=83747572
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210920420.6A Active CN115272881B (zh) | 2022-08-02 | 2022-08-02 | 动态关系蒸馏的长尾遥感图像目标识别方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115272881B (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116758391A (zh) * | 2023-04-21 | 2023-09-15 | 大连理工大学 | 噪声抑制蒸馏的多域遥感目标泛化性识别方法 |
CN117557916A (zh) * | 2024-01-11 | 2024-02-13 | 大连理工大学 | 一种结合文本图像生成的遥感目标分类方法 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA3076424A1 (en) * | 2019-03-22 | 2020-09-22 | Royal Bank Of Canada | System and method for knowledge distillation between neural networks |
CN112184508A (zh) * | 2020-10-13 | 2021-01-05 | 上海依图网络科技有限公司 | 一种用于图像处理的学生模型的训练方法及装置 |
CN113837238A (zh) * | 2021-09-02 | 2021-12-24 | 南京大学 | 一种基于自监督和自蒸馏的长尾图像识别方法 |
CN114155436A (zh) * | 2021-12-06 | 2022-03-08 | 大连理工大学 | 长尾分布的遥感图像目标识别逐步蒸馏学习方法 |
CN114241273A (zh) * | 2021-12-01 | 2022-03-25 | 电子科技大学 | 基于Transformer网络和超球空间学习的多模态图像处理方法及系统 |
-
2022
- 2022-08-02 CN CN202210920420.6A patent/CN115272881B/zh active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA3076424A1 (en) * | 2019-03-22 | 2020-09-22 | Royal Bank Of Canada | System and method for knowledge distillation between neural networks |
CN112184508A (zh) * | 2020-10-13 | 2021-01-05 | 上海依图网络科技有限公司 | 一种用于图像处理的学生模型的训练方法及装置 |
CN113837238A (zh) * | 2021-09-02 | 2021-12-24 | 南京大学 | 一种基于自监督和自蒸馏的长尾图像识别方法 |
CN114241273A (zh) * | 2021-12-01 | 2022-03-25 | 电子科技大学 | 基于Transformer网络和超球空间学习的多模态图像处理方法及系统 |
CN114155436A (zh) * | 2021-12-06 | 2022-03-08 | 大连理工大学 | 长尾分布的遥感图像目标识别逐步蒸馏学习方法 |
Non-Patent Citations (2)
Title |
---|
WENDA ZHAO ET AL.: ""Teaching Teachers First and Then Student: Hierarchical Distillation to Improve Long-Tailed Object Recognition in Aerial Images"", 《IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING》 * |
邓旭冉等: "深度细粒度图像识别研究综述", 《南京信息工程大学学报(自然科学版)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116758391A (zh) * | 2023-04-21 | 2023-09-15 | 大连理工大学 | 噪声抑制蒸馏的多域遥感目标泛化性识别方法 |
CN116758391B (zh) * | 2023-04-21 | 2023-11-21 | 大连理工大学 | 噪声抑制蒸馏的多域遥感目标泛化性识别方法 |
CN117557916A (zh) * | 2024-01-11 | 2024-02-13 | 大连理工大学 | 一种结合文本图像生成的遥感目标分类方法 |
CN117557916B (zh) * | 2024-01-11 | 2024-03-19 | 大连理工大学 | 一种结合文本图像生成的遥感目标分类方法 |
Also Published As
Publication number | Publication date |
---|---|
CN115272881B (zh) | 2023-03-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112308158B (zh) | 一种基于部分特征对齐的多源领域自适应模型及方法 | |
Liu et al. | Knowledge distillation via instance relationship graph | |
CN108564029B (zh) | 基于级联多任务学习深度神经网络的人脸属性识别方法 | |
CN115272881B (zh) | 动态关系蒸馏的长尾遥感图像目标识别方法 | |
CN110443818B (zh) | 一种基于涂鸦的弱监督语义分割方法与系统 | |
Eigen et al. | Nonparametric image parsing using adaptive neighbor sets | |
CN113378906B (zh) | 一种特征自适应对齐的无监督域适应遥感图像语义分割方法 | |
CN112347888B (zh) | 基于双向特征迭代融合的遥感图像场景分类方法 | |
CN107330355B (zh) | 一种基于正样本平衡约束的深度行人再标识方法 | |
CN112883839B (zh) | 基于自适应样本集构造与深度学习的遥感影像解译方法 | |
CN109299707A (zh) | 一种基于模糊深度聚类的无监督行人再识别方法 | |
CN105320961A (zh) | 基于卷积神经网络和支持向量机的手写数字识别方法 | |
CN101315663A (zh) | 一种基于区域潜在语义特征的自然场景图像分类方法 | |
CN114155436B (zh) | 长尾分布的遥感图像目标识别逐步蒸馏学习方法 | |
CN110598018B (zh) | 一种基于协同注意力的草图图像检索方法 | |
CN108121975A (zh) | 一种联合原始数据和生成数据的人脸识别方法 | |
CN113177612B (zh) | 一种基于cnn少样本的农业病虫害图像识别方法 | |
CN109711461A (zh) | 基于主成分分析的迁移学习图片分类方法及其装置 | |
CN111985581A (zh) | 一种基于样本级注意力网络的少样本学习方法 | |
CN103617609B (zh) | 基于图论的k-means非线性流形聚类与代表点选取方法 | |
CN104700100A (zh) | 面向高空间分辨率遥感大数据的特征提取方法 | |
CN116543269B (zh) | 基于自监督的跨域小样本细粒度图像识别方法及其模型 | |
CN110287985A (zh) | 一种基于带变异粒子群算法的可变拓扑结构的深度神经网络图像识别方法 | |
CN117237559A (zh) | 面向数字孪生城市的三维模型数据智能分析方法及系统 | |
CN111125396A (zh) | 一种单模型多分支结构的图像检索方法 |
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 | ||
CB03 | Change of inventor or designer information |
Inventor after: Zhao Wenda Inventor after: Yu Tao Inventor after: Liu Jiani Inventor after: Zhao Fan Inventor after: Liu Xinghui Inventor after: Li Zhili Inventor after: Huang Youpeng Inventor before: Zhao Wenda Inventor before: Yu Tao Inventor before: Liu Jiani Inventor before: Wang Haipeng Inventor before: Zhao Fan Inventor before: Liu Xinghui Inventor before: Li Zhili Inventor before: Huang Youpeng |
|
GR01 | Patent grant | ||
GR01 | Patent grant |