【论文笔记】Transformers in Remote Sensing: A Survey 中的相关论文链接

已于 2022-11-07 22:02:13 修改
阅读量1.7k 收藏 15
点赞数 1
分类专栏： 论文笔记 Transformer系列 文章标签： 深度学习 人工智能 transformer
于 2022-11-07 19:40:54 首次发布
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/m0_61899108/article/details/127737384
版权

目录

Transformer-in-Remote-Sensing:A-Survey

This repo supplements our Transformer in Remote Sensing Survey

VHR Imagery

 Image Classification

Image Detection

Change Detection

Image Segmentation

Building Extraction

Image Captioning

Image Super Resolution

Hyperspectral Imagery

Image Classification

Pan-Sharpening

SAR Imagery

Image Classification

Segmentation

Image Detection

Despeckling

Change Detection

Image Registration

Citation

遥感领域的Transformer综述

综述具体介绍见：【综述】Transformers in Remote Sensing: A Survey_m0_61899108的博客-CSDN博客

Transformer-in-Remote-Sensing:A-Survey

This repo supplements our Transformer in Remote Sensing Survey

Abdulaziz Amer Aleissaee*, Amandeep Kumar*, Rao Muhammad Anwer, Salman Khan, Hisham Cholakkal, Fahad Shahbaz khan

This repo includes the Remote Sensing papers with Transformers which are presented in our paper, and we aim to frequently update the latest relevant papers.

Content

VHR Imagery

 Image Classification

  • Vision transformers for remote sensing image classification [PDF]
  • TRS: Transformers for Remote Sensing Scene Classification [PDF]
  • Two-stream swin transformer with differentiable sobel operator for remote sensing image classification[PDF]
  • When cnns meet vision trans-former: A joint framework for remote sensing scene classification, [PDF]
  • Homo– heterogenous transformer learning framework for rs scene classification [PDF]
  • An Empirical Study of Remote Sensing Pretraining [PDF]

Image Detection

  • An improved swin transformer-based model for remote sensing object detection and instance segmentation [PDF]
  • Transformer with transfer cnn for remote-sensing-image object detection [PDF]
  • Gansformer: A detection network for aerial images with high performance com- bining convolutional network and transformer[PDF]
  • Adt-det: Adaptive dynamic refined single-stage transformer detector for arbitrary- oriented object detection in satellite optical imagery, [PDF]
  • Point rcnn: An angle-free framework for rotated object detection [PDF]
  • Hybrid network model: Transconvnet for oriented object detection in remote sensing images [PDF]
  • Oriented reppoints for aerial object detection [PDF]
  • Oriented object detection with transformer [PDF]
  • Ao2-detr: Arbitrary-oriented object detection transformer [PDF]
  • Few could be better than all: Feature sampling and grouping for scene text detection, [PDF]
  • Rodformer: High- precision design for rotating object detection with transformers, [PDF]

Change Detection

  • Remote sensing image change detection with transformers [PDF]
  • Deep multiscale siamese network with parallel convolutional structure and self-attention for change detection [PDF]
  • Swinsunet: Pure transformer network for remote sensing image change detection [PDF]
  • A network combining a transformer and a convolutional neural network for remote sensing image change detection, [PDF]
  • A hybrid transformer network for change detection in optical remote-sensing images [PDF]
  • Hybrid-transcd: A hybrid transformer remote sensing image change detection network via token aggregation [PDF]

Image Segmentation

  • Stransfuse: Fusing swin transformer and convolutional neural network for remote sensing image semantic segmentation [PDF]
  • Cctnet: Coupled cnn and transformer network for crop segmentation of remote sensing images, [PDF]
  • Transformer and cnn hybrid deep neural network for semantic segmentation of very-high-resolution remote sensing imagery [PDF]
  • Transformer-based decoder designs for semantic segmentation on remotely sensed images [PDF]
  • Efficient transformer for remote sensing image segmentation [PDF]

Building Extraction

  • Building extraction from remote sensing images with sparse token transformers, [PDF]
  • A swin transformer-based encoding booster integrated in u-shaped network for building extraction [PDF]
  • Building extraction with vision transformer [PDF]
  • Transferring transformer-based models for cross-area building extraction from remote sensing images [PDF]

Image Captioning

  • Remote sensing image caption generation via transformer and reinforcement learning, [PDF]
  • Remote-sensing image captioning based on multilayer aggregated transformer [PDF]
  • A mask-guided transformer network with topic token for remote sensing image captioning [PDF]

Image Super Resolution

  • Tr-misr: Multiimage super-resolution based on feature fusion with transformers, [PDF]
  • Transformer-based multistage enhancement for remote sensing image super-resolution [PDF]
  • A super- resolution method of remote sensing image using transformers [PDF]
  • Space-time Super-resolution for Satellite Video: A Joint Framework Based on Multi-Scale Spatial-Temporal Transformer [PDF]

Hyperspectral Imagery

Image Classification

  • Spectralformer: Rethinking hyperspectral image classification with transformers[PDF]
  • Multiscale convolutional transformer with center mask pretraining for hyperspectral image classification [PDF]
  • Multimodal fusion transformer for remote sensing image classification [PDF]
  • Convolutional transformer network for hyperspectral image classification, [PDF]
  • Deep hierarchical vision transformer for hyperspectral and lidar data classification [PDF]
  • Dss-trm: deep spatial–spectral transformer for hyperspectral image classification [PDF]
  • Hyperspectral image trans- former classification networks [PDF]
  • Hsi-bert: Hyperspectral image classification using the bidirectional en- coder representation from transformers [PDF]
  • Spectral–spatial feature tokenization transformer for hyperspectral image classification [PDF]
  • Spectral-spatial transformer network for hyperspectral image classification: A factorized architecture search framework, [PDF]

Pan-Sharpening

  • PanFormer: a Transformer Based Model for Pan-sharpening [PDF]
  • Hypertransformer: A textural and spectral feature fusion transformer for pansharpening [PDF]
  • Pmacnet: Parallel multiscale attention constraint network for pan-sharpening [PDF]
  • Pan-sharpening based on cnn+ pyramid transformer by using no-reference loss, [PDF]
  • Multiscale spatial–spectral interaction transformer for pan-sharpening [PDF]
  • Transformer-based regression network for pansharpening remote sensing images [PDF]

SAR Imagery

Image Classification

  • Exploring vision transformers for polarimetric sar image classification [PDF]
  • High resolution sar image classification using global-local network structure based on vision transformer and cnn [PDF]
  • St-pn: A spatial transformed prototypical network for few-shot sar image classification [PDF]

Segmentation

  • Gcbanet: A global context boundary-aware network for sar ship instance segmentation[PDF]

Image Detection

  • Crtranssar: A visual transformer based on contextual joint representation learning for sar ship detection [PDF]
  • Geospatial transformer is what you need for aircraft detection in sar imagery [PDF]
  • Sfre-net: Scattering feature relation enhancement network for aircraft detection in sar images [PDF]
  • End-to-end method with transformer for 3d detection of oil tank from single sar image, [PDF]

Despeckling

  • Transformer based sar image despeckling [PDF]

Change Detection

  • A contrastive learning transformer for change detection in highresolution sar images [PDF]

Image Registration

  • A transformer-based coarse-tofine wide-swath sar image registration method under weak texture conditions [PDF]

 

m0_61899108
关注
  • 1
    点赞
  • 踩
  • 15
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
专栏目录
remote-sensing-image-captioning:遥感图像字幕论文的体系结构
03-14
遥感图像字幕 遥感图像字幕论文的体系结构
高光谱分类论文解读分享之基于多模态融合Transformer的遥感图像分类方法
sinat_41421587的博客
01-09 1070
IEEE TGRS 2023：基于多模态融合Transformer的遥感图像分类方法
CCF A类会议或期刊----近两年聚类相关论文
Thincor的博客
03-21 5461
会议/期刊 论文 sigmod2021 Fast Density-Peaks Clustering: Multicore-based Parallelization Approach. sigmod2021 SharPer: Sharding Permissioned Blockchains Over Network Clusters. sigmod2021 Dynamic Structural Clustering on Graphs. sigmod2021 On Saving....
21年 46篇神经架构搜索(Neural Architecture Search) ICCV CVPR Survey 笔记 (1-20)
miss_the_boat的博客
03-11 6905
1. FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining 2.Activate or Not: Learning Customized Activation 3.Dynamic Slimmable Network 4.AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
2020：MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering
weixin_42653320的博客
09-24 479
摘要 我们提出MMFT-BERT来解决，VQA确保多个输入模态的单个和结合处理。我们的方法受益于分别采用BERT编码并使用一个新的基于transformer的融合模型处理多模态数据。我们的方法将不同模态分为具有相似结构的不同BERT实例，但权重可变。在TVQA中实现了SOTA结果。此外，我们提供了TVQA-visual，一种孤立的诊断子集，严格需要基于人类注释者的判断的视觉模态知识。这组问题帮助我们研究模型行为，以及TVQA不能超过人类表现的挑战。大量实验表明我们方法的有效性和优越性。 ...
遥感图像处理笔记之【论文：一种图像融合新方法】
最新发布
rvdgdsva的博客
01-26 1206
遥感系列第12篇.遥感图像处理方向的学习者可以参考或者复刻
建筑物提取 Building Extraction 算法论文
晞行的博客
04-20 3368
建筑物提取方法及代码
[论文笔记]SwinSUNet: Pure Transformer Network for Remote Sensing Image Change Detection
lmt_like的博客
09-24 2242
SwinSUNet，一个具有Siamese U形结构的纯Swin transformer网络。这是第一个基于纯transformer的CD网络。
Transformers in Remote Sensing: A Survey
qq_52302919的博客
09-30 1888
CNN的主要组成部分之一是卷积运算，它捕获输入图像中元素（如轮廓和边缘信息）之间的局部联系。CNN编码偏置，例如空间连接性和平移等方差。这些特征有助于构建通用高效的体系结构。然而，CNN中的局部感受野限制了对图像中长距离依赖关系的建模（例如，远距离部分关系）。此外，卷积与内容无关，因为卷积滤波器权重是稳定的，无论其性质如何，对所有输入应用相同的权重。最近，视觉Transformers（ViTs）在计算机视觉的各种任务中表现出令人印象深刻的性能。
2021.02.01 Visual QA论文阅读
lch的博客
02-01 407
目录[2015][NIPS] Are You Talking to a Machine Dataset and Methods for Multilingual Image Question Answering[2015][NIPS] Exploring Models and Data for Image Question Answering [2015][NIPS] Are You Talking to a Machine Dataset and Methods for Multilingual Imag
Efficient Transformers： A Survey.pdf
09-17
Efficient Transformers： A Survey，这是2020年关于Transformer的综述，感兴趣的可以下载
A Survey of Visual Transformers 2021.pdf
11-29
A Survey of Visual Transformers 2021.pdf
Transformers in Vision A Survey.pdf
09-25
Transformers in Vision A Survey.pdf
Transformers in Vision A Survey.zip
09-23
Transformers in Vision A Survey.zip
DETR- End-to-End Object Detection with Transformers 论文解析Yannic Kilcher版本
06-14
DETR- End-to-End Object Detection with Transformers (Paper Explained)，来自需要你懂得的网站视频，生肉版本。
高光谱数据集，论文笔记，图像融合代码汇总
每天都要看论文
10-31 9063
数据集：https://blog.csdn.net/siyumiao_hbu/article/details/109291055 论文笔记： 高光谱图像超分辨率空间谱先验学习Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery GDD无监督图像对融合Guided Deep Decoder: Unsupervised Image Pair Fusion 用于半盲高光谱和多光谱图像融合的非局部稀疏张..
论文阅读：multimodal remote sensing survey 遥感多模态综述
qq_42740834的博客
01-13 7708
从多模态表示，对齐，融合，跨模态转换，协同学习等5个大方面来介绍在遥感领域的分类和相关工作
SMESwin Unet：融合CNN和Transformer进行医学图像分割
qq_45745941的博客
05-30 1694
视觉Transformer 是自去年以来医学图像分割领域最受欢迎的新范式，在定量指标上超过了传统的CNN。ViTs的显著优点是利用注意力层来对token之间的全局关系进行建模。然而，ViTs表达能力的提高也带来了相应的缺点：缺乏CNN的归纳偏差（局部性）、翻译不变性和视觉信息的层次结构。因此，训练有素的ViT比CNN需要更多的数据。由于医学成像领域的高质量数据总是有限的，我们提出了SMESwin-UNet。本文方法。
Transformers在自动驾驶领域的应用（High-level like in scene）
qq_39337332的博客
04-26 1212
Transformers uses global attention mechanism to capture long-range interaction information. Two core modules in Transformers are Self-Attention and Cross-Attention, which defined asAttn(Q,K,V)=softmax(QK⊤dk)VSelfAttn(X)=Attn(WQX,WKX,WVX)CrossAttn(X,Y)=Attn
Transformer-Based Visual Segmentation: A Survey
05-24
Visual segmentation is one of the most important tasks in computer vision, which involves dividing an image into multiple segments, each of which corresponds to a different object or region of interest in the image. In recent years, transformer-based methods have emerged as a promising approach for visual segmentation, leveraging the self-attention mechanism to capture long-range dependencies in the image. This survey paper provides a comprehensive overview of transformer-based visual segmentation methods, covering their underlying principles, architecture, training strategies, and applications. The paper starts by introducing the basic concepts of visual segmentation and transformer-based models, followed by a discussion of the key challenges and opportunities in applying transformers to visual segmentation. The paper then reviews the state-of-the-art transformer-based segmentation methods, including both fully transformer-based approaches and hybrid approaches that combine transformers with other techniques such as convolutional neural networks (CNNs). For each method, the paper provides a detailed description of its architecture and training strategy, as well as its performance on benchmark datasets. Finally, the paper concludes with a discussion of the future directions of transformer-based visual segmentation, including potential improvements in model design, training methods, and applications. Overall, this survey paper provides a valuable resource for researchers and practitioners interested in the field of transformer-based visual segmentation.

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
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
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