CN112907600A - 目标检测模型的优化方法及系统 - Google Patents
目标检测模型的优化方法及系统 Download PDFInfo
- Publication number
- CN112907600A CN112907600A CN202110260170.3A CN202110260170A CN112907600A CN 112907600 A CN112907600 A CN 112907600A CN 202110260170 A CN202110260170 A CN 202110260170A CN 112907600 A CN112907600 A CN 112907600A
- Authority
- CN
- China
- Prior art keywords
- image
- shuffling
- convolution
- channels
- multiplied
- 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 25
- 238000001514 detection method Methods 0.000 title claims abstract description 17
- 238000005457 optimization Methods 0.000 title claims abstract description 9
- 238000010586 diagram Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 abstract description 7
- 239000011159 matrix material Substances 0.000 description 10
- 239000013256 coordination polymer Substances 0.000 description 2
- 101150064138 MAP1 gene Proteins 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (6)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110260170.3A CN112907600B (zh) | 2021-03-10 | 2021-03-10 | 目标检测模型的优化方法及系统 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110260170.3A CN112907600B (zh) | 2021-03-10 | 2021-03-10 | 目标检测模型的优化方法及系统 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112907600A true CN112907600A (zh) | 2021-06-04 |
CN112907600B CN112907600B (zh) | 2024-05-24 |
Family
ID=76108340
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110260170.3A Active CN112907600B (zh) | 2021-03-10 | 2021-03-10 | 目标检测模型的优化方法及系统 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112907600B (zh) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106095392A (zh) * | 2016-06-20 | 2016-11-09 | 龙芯中科技术有限公司 | 混洗模式生成方法和装置 |
CN109829868A (zh) * | 2019-02-28 | 2019-05-31 | 华南理工大学 | 一种轻量级深度学习模型图像去雾方法、电子设备及介质 |
CN110309876A (zh) * | 2019-06-28 | 2019-10-08 | 腾讯科技(深圳)有限公司 | 目标检测方法、装置、计算机可读存储介质和计算机设备 |
CN110532878A (zh) * | 2019-07-26 | 2019-12-03 | 中山大学 | 一种基于轻量化卷积神经网络的驾驶员行为识别方法 |
GB201919298D0 (en) * | 2019-12-24 | 2020-02-05 | Nchain Holdings Ltd | Computer-implemented system and method |
CN111259983A (zh) * | 2020-02-13 | 2020-06-09 | 电子科技大学 | 基于深度学习的图像语义分割方法及存储介质 |
US10713589B1 (en) * | 2016-03-03 | 2020-07-14 | Amazon Technologies, Inc. | Consistent sort-based record-level shuffling of machine learning data |
CN111445019A (zh) * | 2020-04-30 | 2020-07-24 | 南京大学 | 一种分组卷积中通道混洗操作的实现装置及方法 |
US20200349426A1 (en) * | 2019-04-30 | 2020-11-05 | Samsung Electronics Co., Ltd. | Convolution streaming engine for deep neural networks |
CN111914987A (zh) * | 2019-05-10 | 2020-11-10 | 北京京东尚科信息技术有限公司 | 基于神经网络的数据处理方法及装置、设备和可读介质 |
US20200401847A1 (en) * | 2019-06-24 | 2020-12-24 | Realtek Semiconductor Corp. | Calculation method using pixel-channel shuffle convolutional neural network and operating system using the same |
CN112418418A (zh) * | 2020-11-11 | 2021-02-26 | 江苏禹空间科技有限公司 | 基于神经网络的数据处理方法、装置、存储介质及服务器 |
-
2021
- 2021-03-10 CN CN202110260170.3A patent/CN112907600B/zh active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10713589B1 (en) * | 2016-03-03 | 2020-07-14 | Amazon Technologies, Inc. | Consistent sort-based record-level shuffling of machine learning data |
CN106095392A (zh) * | 2016-06-20 | 2016-11-09 | 龙芯中科技术有限公司 | 混洗模式生成方法和装置 |
CN109829868A (zh) * | 2019-02-28 | 2019-05-31 | 华南理工大学 | 一种轻量级深度学习模型图像去雾方法、电子设备及介质 |
US20200349426A1 (en) * | 2019-04-30 | 2020-11-05 | Samsung Electronics Co., Ltd. | Convolution streaming engine for deep neural networks |
CN111914987A (zh) * | 2019-05-10 | 2020-11-10 | 北京京东尚科信息技术有限公司 | 基于神经网络的数据处理方法及装置、设备和可读介质 |
US20200401847A1 (en) * | 2019-06-24 | 2020-12-24 | Realtek Semiconductor Corp. | Calculation method using pixel-channel shuffle convolutional neural network and operating system using the same |
CN110309876A (zh) * | 2019-06-28 | 2019-10-08 | 腾讯科技(深圳)有限公司 | 目标检测方法、装置、计算机可读存储介质和计算机设备 |
CN110532878A (zh) * | 2019-07-26 | 2019-12-03 | 中山大学 | 一种基于轻量化卷积神经网络的驾驶员行为识别方法 |
GB201919298D0 (en) * | 2019-12-24 | 2020-02-05 | Nchain Holdings Ltd | Computer-implemented system and method |
CN111259983A (zh) * | 2020-02-13 | 2020-06-09 | 电子科技大学 | 基于深度学习的图像语义分割方法及存储介质 |
CN111445019A (zh) * | 2020-04-30 | 2020-07-24 | 南京大学 | 一种分组卷积中通道混洗操作的实现装置及方法 |
CN112418418A (zh) * | 2020-11-11 | 2021-02-26 | 江苏禹空间科技有限公司 | 基于神经网络的数据处理方法、装置、存储介质及服务器 |
Non-Patent Citations (3)
Title |
---|
CAN CHEN;LUCA ZANOTTI FRAGONARA;ANTONIOS TSOURDOS: "Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutions", APPLIED SCIENCES, vol. 10, no. 2391, 31 December 2020 (2020-12-31) * |
GOPAL CHANDRA JANA;RATNA SHARMA;ANUPAM AGRAWAL: "A 1D-CNN-Spectrogram Based Approach for Seizure Detection from EEG Signal", PROCEDIA COMPUTER SCIENCE, vol. 167, 31 December 2020 (2020-12-31), XP086133267, DOI: 10.1016/j.procs.2020.03.248 * |
郭彤宇;王博;刘悦;魏颖: "多通道融合可分离卷积神经网络下的脑部磁共振图像分割", 中国图象图形学报, vol. 24, no. 011, 31 December 2019 (2019-12-31) * |
Also Published As
Publication number | Publication date |
---|---|
CN112907600B (zh) | 2024-05-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107340993B (zh) | 运算装置和方法 | |
WO2021004366A1 (zh) | 基于结构化剪枝和低比特量化的神经网络加速器及方法 | |
CN109934331B (zh) | 用于执行人工神经网络正向运算的装置和方法 | |
CN111445418B (zh) | 图像去雾处理方法、装置及计算机设备 | |
CN111030861B (zh) | 一种边缘计算分布式模型训练方法、终端和网络侧设备 | |
CN108629291B (zh) | 一种抗网格效应的人脸深度预测方法 | |
CN110060236B (zh) | 基于深度卷积神经网络的立体图像质量评价方法 | |
CN116416561A (zh) | 一种视频图像处理方法和装置 | |
CN109543815B (zh) | 神经网络的加速方法及装置 | |
WO2020233709A1 (zh) | 模型压缩方法及装置 | |
CN107832794A (zh) | 一种卷积神经网络生成方法、车系识别方法及计算设备 | |
CN112288087A (zh) | 一种神经网络剪枝方法、装置、电子设备及存储介质 | |
Geng et al. | A stereoscopic image quality assessment model based on independent component analysis and binocular fusion property | |
CN111652921A (zh) | 一种单目深度预测模型的生成方法及单目深度预测方法 | |
CN111553296A (zh) | 一种基于fpga实现的二值神经网络立体视觉匹配方法 | |
CN109697083B (zh) | 数据的定点化加速方法、装置、电子设备及存储介质 | |
CN111882053A (zh) | 一种基于拼接卷积的神经网络模型压缩方法 | |
Messai et al. | End-to-end deep multi-score model for no-reference stereoscopic image quality assessment | |
CN112907600A (zh) | 目标检测模型的优化方法及系统 | |
Zhang | Seesaw-net: convolution neural network with uneven group convolution | |
CN111339315A (zh) | 知识图谱构建方法、系统、计算机可读介质和电子设备 | |
CN116383639A (zh) | 一种生成对抗网络的知识蒸馏方法、装置、设备及存储介质 | |
CN114885144B (zh) | 基于数据融合的高帧率3d视频生成方法及装置 | |
CN113159297B (zh) | 一种神经网络压缩方法、装置、计算机设备及存储介质 | |
CN115984934A (zh) | 人脸位姿估计模型的训练方法、人脸位姿估计方法及装置 |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220107 Address after: 2209-c1, No. 19, Erquan East Road, Huizhi enterprise center, Xishan District, Wuxi City, Jiangsu Province, 214000 Applicant after: Wuxi yuspace Intelligent Technology Co.,Ltd. Address before: Room 1101, block C, Kangyuan smart port, No. 50, Jiangdong Street, Jialing, Jianye District, Nanjing City, Jiangsu Province, 210000 Applicant before: Jiangsu Yu Space Technology Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220919 Address after: Room 1101, block C, Kangyuan smart port, No. 50, Jiangdong Street, Jialing, Jianye District, Nanjing City, Jiangsu Province, 210000 Applicant after: Jiangsu Yu Space Technology Co.,Ltd. Address before: 2209-c1, No. 19, Erquan East Road, Huizhi enterprise center, Xishan District, Wuxi City, Jiangsu Province, 214000 Applicant before: Wuxi yuspace Intelligent Technology Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20230829 Address after: 2209-c1, No. 19, Erquan East Road, Huizhi enterprise center, Xishan District, Wuxi City, Jiangsu Province, 214000 Applicant after: Wuxi yuspace Intelligent Technology Co.,Ltd. Address before: Room 1101, block C, Kangyuan smart port, No. 50, Jiangdong Street, Jialing, Jianye District, Nanjing City, Jiangsu Province, 210000 Applicant before: Jiangsu Yu Space Technology Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |