YOLOv11 改进 - 注意力机制 | IIA信息整合注意力(Information Integration Attention ):精准保留空间位置信息,平衡精度与计算成本 | TGRS2025

前言

本文提出信息整合注意力(IIA)机制,并将其集成到YOLOv11中用于遥感图像语义分割。传统CNN难捕捉全局信息,Transformer计算复杂,现有基于Mamba的方法未充分考虑局部信息。IIA利用图像特征空间位置不变性,先融合编解码器特征,再从高度和宽度方向提取序列信息,生成注意力权重因子动态调制特征。其通过通道级拼接、双方向拆分与池化、轻量级1D卷积和残差融合等操作,平衡了精度与计算成本。实验表明,集成IIA的YOLOv11在数据集上提高了精度,且运行高效。

文章目录: YOLOv11改进大全:卷积层、轻量化、注意力机制、损失函数、Backbone、SPPF、Neck、检测头全方位优化汇总

专栏链接: YOLOv11改进专栏

介绍

image-20251223215226508

摘要

YOLO目标检测的IIA注意力模块优化实践 注意力机制是提升深度学习模型性能的关键技术,通过模拟人类视觉的聚焦机制,能够有效增强模型对重要特征的提取能力。IIA(Information Integration Attention)模块作为新型注意力机制,采用双路径设计整合局部细节与全局上下文,在保持YOLO算法实时性的同时显著提升检测精度。该技术通过可变形卷积实现位置感知,结合改进的金字塔池化捕获多尺度特征,并引入自适应门控动态融合信息。在目标检测、语义分割等计算机视觉任务中,这类注意力机制能有效解决小目标检测和复杂背景干扰等工程难题,其中在COCO 阅读详情

相关推荐

YOLOv11改进系列 | 原创改进C3k2_GhostDynamicConv模块,Ghost动态卷积轻量替换C3k2,精度效率更均衡

本文提出了一种轻量化的YOLOv11-seg改进方法,通过将C3k2模块替换为C3k2_GhostDynamicConv,结合Ghost模块和动态卷积路由,在保持计算量不变的同时提升模型表达能力。改进后的模块采用主分支动态卷积生成核心特征,廉价分支动态depthwise卷积扩展特征的方式,实现参数仅增加2.45%但GFLOPs不变的轻量化改进。实验表明,该方法在目标检测和分割任务中实现了轻量化和精度提升的良好平衡,适用于部署友好型应用场景。

qq_44224801的博客 282

YOLO11改进 | 融合改进 | C3k2融合 Context Anchor Attention 【两个版本融合-独家创新】

yolo11,yolo11改进,融合创新,独家改进

kay_545 2385

YOLO11改进 | 模块缝合 | C3k2融合多尺度表征学习模块 【两种改进】

yolo11改进,yolo11发论文,yolo11

kay_545 2047

YOLOv11改进 - C3k2融合 | C3k2融合 IIA信息整合注意力(Information Integration Attention )平衡精度与计算成本 | TGRS2025

本文提出信息整合注意力(IIA)机制,并将其集成到YOLOv11中用于遥感图像语义分割。传统CNN和Transformer方法分别存在难以捕捉全局信息和计算复杂的问题,现有基于Mamba的方法也未充分考虑局部信息。IIA机制利用图像特征空间位置不变性,通过基础信息融合、双方向序列提取和动态权重调制三个核心步骤,以及通道级拼接、双方向拆分与池化、轻量级1D卷积和残差融合四个关键操作,实现了轻量与精准的平衡。我们将IIA集成到YOLOv11的C3k2模块中。实验表明,改进后的YOLOv11在多个数据集上提高了精

魔改工程师的博客 465

YOLO11改进大全:卷积层、轻量化、注意力机制、损失函数、Backbone、SPPF、Neck、检测头全方位优化汇总

YOLOv11改进大全:卷积层、轻量化、注意力机制、损失函数、Backbone、SPPF、Neck、检测头全方位优化汇总

魔改工程师的博客 4590

YOLO系列算法改进 | C3k2改进篇 | 融合DEConv细节增强卷积模块 | 细节增强+多分支差分卷积融合,标准卷积的完美涨点替代! | TIP 2024

YOLO系列算法改进 | C3k2改进篇 | 融合DEConv细节增强卷积模块 | 细节增强+多分支差分卷积融合,标准卷积的完美涨点替代! | TIP 2024 (以YOLO26最新目标检测模型为基础,融合C3k2_DEConv创新模块进行改进)

2502_91881744的博客 319

YOLOv11改进 | RCS-OSA与C3k2融合架构技术详解

跨尺度特征金字塔:5级特征无损融合全空间注意力:HWD三维关系建模残差加速设计:深层网络训练优化智慧城市:密集人群计数误差降低12%自动驾驶:夜间检测mAP提升7.9%工业质检:缺陷分类F1-score提升9.3%标准YOLOv11集成实现TensorRT加速插件Android NNAPI部署示例多场景预训练模型动态稀疏注意力3D点云扩展自监督预训练。

weixin_39818775的博客 1277

AI编程实战:YOLO11道路坑洼检测实战,从数据集准备到模型训练与结果分析(附完整Prompt)

Prompt 9:使用 best.pt 进行检测现在我已经完成 YOLO11 道路坑洼检测模型训练。训练得到的最佳权重文件路径为:xxxxxx请根据当前项目实际路径,帮我编写一个自定义模型图片检测脚本。要求:1. 加载刚刚训练得到的 best.pt;2. 支持指定单张图片进行检测;3. 支持指定图片文件夹进行检测;4. 使用 YOLO11 目标检测接口;5. 保存检测结果;6. 输出检测结果图片的保存路径;7. 不要修改原始图片;

在职AI算法工程师,擅长计算机视觉,YOLO目标检测、分割等,擅长web、pyqt界面可视化,好内容持续更新中,来这里跟大家一起学习,共同进步 58

YOLO训练调优与问题诊断实战,从损失震荡到mAP异常的全链路排查

本文系统梳理YOLO训练中的常见问题,构建从现象到根因的诊断框架,涵盖损失不降、mAP异常、震荡与NaN等典型故障。通过监控梯度范数、正样本分布、特征图等关键信号,结合控制变量法,精准定位数据标注、学习率、增强策略、优化器配置等问题。重点解析学习率调度、梯度裁剪、EMA、混合精度训练等调优技巧,提供可复用的排查checklist与PyTorch监控代码,助力实现高效、稳定的模型训练。

QQ_778132974的博客 29

【教程】安装 iterm2 打造漂亮且高性能的 mac 终端

最近电脑重新安装系统,开发环境和软件都需要重新安装和配置,其中终端工具是必不可少的,正好利用这个机会,介绍一下 macOS 终端神器 iTerm2 的安装和配置,并推荐几款好用的插件和工具。在IT领域中,工具的选择和使用对于开发者和运维人员来说至关重要。而在众多终端模拟器中,ITerm2无疑是一个出色的选择,希望本篇的文章能对你有些帮助,感兴趣的朋友可以登录官网查看官方文档。我是刘大大,持续分享AI相关领域的知识和工具,喜欢点点关注。

刘大大AI的博客 3409

从零开始:用Neo4j构建你的第一个知识图谱(附完整代码示例)

本文提供了一份从零开始的Neo4j知识图谱构建实战指南。通过一个“经典科幻电影宇宙”的具体案例,手把手教你安装环境、设计图谱模式,并使用Cypher查询语言完成节点与关系的创建、数据查询及可视化,帮助你快速掌握自下而上构建知识图谱的核心技能。

weixin_29053073的博客 476

Windows/Linux双平台实战:QtCreator构建套件配置全攻略(含GCC/G++/GDB/CMake)

本文详细介绍了在Windows和Linux双平台下配置QtCreator构建套件的完整流程,涵盖GCC/G++、GDB和CMake等核心工具链的设置技巧。通过分步指导和实用示例,帮助开发者解决跨平台开发中的配置难题,提升Qt应用开发效率。特别针对QtCreator新手和需要在多平台切换的开发者提供了全面的配置指南。

weixin_28836507的博客 472

Windows 11安装realtek audio control

Windows 11安装realtek audio control,解决无法链接RPC问题

m0_46144825的博客 8万+

从零开始:QNX SDP 8.0开发环境搭建与实战入门

本文详细介绍了如何从零开始搭建QNX SDP 8.0开发环境并进行实战入门。内容涵盖许可证获取、环境安装、命令行与IDE工具使用、BSP构建、系统镜像生成,以及编写、编译和运行第一个QNX程序的全过程。旨在帮助嵌入式开发者,特别是汽车电子和工业控制领域的工程师,快速掌握这一实时操作系统(RTOS)的开发基础。

weixin_29163857的博客 648

systemView的安装使用

systemView的安装使用

qq_33712422的博客 3999

S32DS新建工程、编译调试下载、导入工程详细介绍

新建了一个工程之后,下面简单介绍下基本的UI界面。其中最左下角那个是界面,这个界面很重要,是图形化配置界面,然后可以根据这些配置自动生成代码。其中,左边那些配置文件,都是系统帮我们创建好了的,我们其实可以直接用就行。有PE工具的调试,以及Jlink工具的调试。我目前使用到PE工具调试可以查看寄存器值,而Jlink调试查看不了寄存器值。连接了开发板之后,点击Debug就可以吧程序下载到芯片上了,而且可以进入到调试界面。

luobeihai的博客 2万+

libero烧录信号抓取

提示:如果改了东西需要重新烧录,需要把这两个界面都关闭再libero打开。两个红色的要关闭掉。然后返回libero开始烧录,观测信号(如果只烧录观测从这一步开始就行)等到下面的messige出现以下信息表示run好了。在下图中右侧可以自己设置,设置完之后记得保存一下。run一下,耐心等待,有警告就ok,run完之后。run成功会变绿色,然后点下面的这个看波形。设置抓取信号:在libero打开。打开的就是烧录界面,直接run。

qq_34047965的博客 1433

深度学习工具包 DeepLearningToolbox

深度学习工具包Deprecation notice.-----This toolbox is outdated and no longer maintained.There are much better tools available for deep learning than this toolbox, e.g. [Theano](http://deeplearning.net/software/theano/), [torch](http://torch.ch/) or [tensorflow](http://www.tensorflow.org/)I would suggest you use one of the tools mentioned above rather than use this toolbox.Best, Rasmus.DeepLearnToolbox================A Matlab toolbox for Deep Learning.Deep Learning is a new subfield of machine learning that focuses on learning deep hierarchical models of data.It is inspired by the human brain's apparent deep (layered, hierarchical) architecture.A good overview of the theory of Deep Learning theory is[Learning Deep Architectures for AI](http://www.iro.umontreal.ca/~bengioy/papers/ftml_book.pdf)For a more informal introduction, see the following videos by Geoffrey Hinton and Andrew Ng.* [The Next Generation of Neural Networks](http://www.youtube.com/watch?v=AyzOUbkUf3M) (Hinton, 2007)* [Recent Developments in Deep Learning](http://www.youtube.com/watch?v=VdIURAu1-aU) (Hinton, 2010)* [Unsupervised Feature Learning and Deep Learning](http://www.youtube.com/watch?v=ZmNOAtZIgIk) (Ng, 2011)If you use this toolbox in your research please cite [Prediction as a candidate for learning deep hierarchical models of data](http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=6284)```@MASTERSTHESIS\{IMM2012-06284, author = "R. B. Palm", title = "Prediction as a candidate for learning deep hierarchical models of data", year = "2012",}```Contact: rasmusbergpalm at gmail dot comDirectories included in the toolbox-----------------------------------`NN/` - A library for Feedforward Backpropagation Neural Networks`CNN/` - A library for Convolutional Neural Networks`DBN/` - A library for Deep Belief Networks`SAE/` - A library for Stacked Auto-Encoders`CAE/` - A library for Convolutional Auto-Encoders`util/` - Utility functions used by the libraries`data/` - Data used by the examples`tests/` - unit tests to verify toolbox is workingFor references on each library check REFS.mdSetup-----1. Download.2. addpath(genpath('DeepLearnToolbox'));Example: Deep Belief Network---------------------```matlabfunction test_example_DBNload mnist_uint8;train_x = double(train_x) / 255;test_x = double(test_x) / 255;train_y = double(train_y);test_y = double(test_y);%% ex1 train a 100 hidden unit RBM and visualize its weightsrand('state',0)dbn.sizes = [100];opts.numepochs = 1;opts.batchsize = 100;opts.momentum = 0;opts.alpha = 1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);figure; visualize(dbn.rbm{1}.W'); % Visualize the RBM weights%% ex2 train a 100-100 hidden unit DBN and use its weights to initialize a NNrand('state',0)%train dbndbn.sizes = [100 100];opts.numepochs = 1;opts.batchsize = 100;opts.momentum = 0;opts.alpha = 1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);%unfold dbn to nnnn = dbnunfoldtonn(dbn, 10);nn.activation_function = 'sigm';%train nnopts.numepochs = 1;opts.batchsize = 100;nn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.10, 'Too big error');```Example: Stacked Auto-Encoders---------------------```matlabfunction test_example_SAEload mnist_uint8;train_x = double(train_x)/255;test_x = double(test_x)/255;train_y = double(train_y);test_y = double(test_y);%% ex1 train a 100 hidden unit SDAE and use it to initialize a FFNN% Setup and train a stacked denoising autoencoder (SDAE)rand('state',0)sae = saesetup([784 100]);sae.ae{1}.activation_function = 'sigm';sae.ae{1}.learningRate = 1;sae.ae{1}.inputZeroMaskedFraction = 0.5;opts.numepochs = 1;opts.batchsize = 100;sae = saetrain(sae, train_x, opts);visualize(sae.ae{1}.W{1}(:,2:end)')% Use the SDAE to initialize a FFNNnn = nnsetup([784 100 10]);nn.activation_function = 'sigm';nn.learningRate = 1;nn.W{1} = sae.ae{1}.W{1};% Train the FFNNopts.numepochs = 1;opts.batchsize = 100;nn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.16, 'Too big error');```Example: Convolutional Neural Nets---------------------```matlabfunction test_example_CNNload mnist_uint8;train_x = double(reshape(train_x',28,28,60000))/255;test_x = double(reshape(test_x',28,28,10000))/255;train_y = double(train_y');test_y = double(test_y');%% ex1 Train a 6c-2s-12c-2s Convolutional neural network %will run 1 epoch in about 200 second and get around 11% error. %With 100 epochs you'll get around 1.2% errorrand('state',0)cnn.layers = { struct('type', 'i') %input layer struct('type', 'c', 'outputmaps', 6, 'kernelsize', 5) %convolution layer struct('type', 's', 'scale', 2) %sub sampling layer struct('type', 'c', 'outputmaps', 12, 'kernelsize', 5) %convolution layer struct('type', 's', 'scale', 2) %subsampling layer};cnn = cnnsetup(cnn, train_x, train_y);opts.alpha = 1;opts.batchsize = 50;opts.numepochs = 1;cnn = cnntrain(cnn, train_x, train_y, opts);[er, bad] = cnntest(cnn, test_x, test_y);%plot mean squared errorfigure; plot(cnn.rL);assert(er<0.12, 'Too big error');```Example: Neural Networks---------------------```matlabfunction test_example_NNload mnist_uint8;train_x = double(train_x) / 255;test_x = double(test_x) / 255;train_y = double(train_y);test_y = double(test_y);% normalize[train_x, mu, sigma] = zscore(train_x);test_x = normalize(test_x, mu, sigma);%% ex1 vanilla neural netrand('state',0)nn = nnsetup([784 100 10]);opts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samples[nn, L] = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.08, 'Too big error');%% ex2 neural net with L2 weight decayrand('state',0)nn = nnsetup([784 100 10]);nn.weightPenaltyL2 = 1e-4; % L2 weight decayopts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex3 neural net with dropoutrand('state',0)nn = nnsetup([784 100 10]);nn.dropoutFraction = 0.5; % Dropout fraction opts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex4 neural net with sigmoid activation functionrand('state',0)nn = nnsetup([784 100 10]);nn.activation_function = 'sigm'; % Sigmoid activation functionnn.learningRate = 1; % Sigm require a lower learning rateopts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex5 plotting functionalityrand('state',0)nn = nnsetup([784 20 10]);opts.numepochs = 5; % Number of full sweeps through datann.output = 'softmax'; % use softmax outputopts.batchsize = 1000; % Take a mean gradient step over this many samplesopts.plot = 1; % enable plottingnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex6 neural net with sigmoid activation and plotting of validation and training error% split training data into training and validation datavx = train_x(1:10000,:);tx = train_x(10001:end,:);vy = train_y(1:10000,:);ty = train_y(10001:end,:);rand('state',0)nn = nnsetup([784 20 10]); nn.output = 'softmax'; % use softmax outputopts.numepochs = 5; % Number of full sweeps through dataopts.batchsize = 1000; % Take a mean gradient step over this many samplesopts.plot = 1; % enable plottingnn = nntrain(nn, tx, ty, opts, vx, vy); % nntrain takes validation set as last two arguments (optionally)[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');```[![Bitdeli Badge](https://d2weczhvl823v0.cloudfront.net/rasmusbergpalm/deeplearntoolbox/trend.png)](https://bitdeli.com/free "Bitdeli Badge")

Data-Structures-and-Algorithm-Analysis-in-Java.pdf

作者: Weiss, Mark A. 出版社: Addison Wesley Data Structures and Algorithm Analysis in Java is an “advanced algorithms” book that fits between traditional CS2 and Algorithms Analysis courses. In the old ACM Curriculum Guidelines, this course was known as CS7. This text is for readers who want to learn good programming and algorithm analysis skills simultaneously so that they can develop such programs with the maximum amo...

Devexpress16.2.6破解工具

Devexpress16.2.6破解工具Devexpress16.2.6破解工具Devexpress16.2.6破解工具Devexpress16.2.6破解工具

LinePhone3.2.7(android端最新版本) sip客户端

SIP客户端For android:LinePhone3.2.7(最新版本),官网地址:http://www.linphone.org/

上一篇: YOLOv11 改进 - C2PSA | C2PSA融合Mask Attention掩码注意力,可学习掩码矩阵破解低分辨率特征提取难题 | 2025 预印
下一篇: YOLOv11改进 - C3k2融合 | C3k2融合 IIA信息整合注意力(Information Integration Attention )平衡精度与计算成本 | TGRS2025
魔改工程师
博客等级 码龄3年 2899粉丝 503原创
评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付:10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

魔改工程师

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值
⌂ 换网址