遥感分割和图像融合近期论文阅读

1、Foreground-Aware Relation Network for Geospatial Object Segmentation inHigh Spatial Resolution Remote Sensing Imagery
前后背景分割
https://openaccess.thecvf.com/content_CVPR_2020/papers/Zheng_Foreground-Aware_Relation_Network_for_Geospatial_Object_Segmentation_in_High_Spatial_CVPR_2020_paper.pdf

2、Effective Use of Dilated Convolutions for Segmenting SmallObjectInstancesin Remote Sensing Imagery
空洞卷积膨胀系数由大到小
https://arxiv.org/ftp/arxiv/papers/1709/1709.00179.pdf

3、Improved Road Connectivity by Joint Learning of Orientation and Segmentation
基于方向向量，道路分割方向学习
https://anilbatra2185.github.io/papers/RoadConnectivityCVPR2019.pdf

4、DiResNet: Direction-aware Residual Network for Road Extraction in VHR Remote Sensing Images
对路网方向进行分类，道路分割方向学习+4个loss
https://arxiv.org/pdf/2005.07232v2.pdf

5、SCAttNet: Semantic Segmentation Network with Spatial and Channel Attention Mechanism for High-Resolution Remote Sensing Images
通道注意力+空间注意力 CBAM
https://arxiv.org/pdf/1912.09121v2.pdf

6、Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks
利用GAN网络用于遥感分割完成数据集迁移学习
https://arxiv.org/pdf/2008.04021v1.pdf

7、HeatNet: Bridging the Day-Night Domain Gap in SemanticSegmentation with Thermal Images
利用白天的可见光和红外分割数据集模型泛化到白天、夜间可见光和红外的多模泛化模型，进行白天迁移到白天和夜间的学习
https://arxiv.org/pdf/2003.04645.pdf

8、MFNet: Towards Real-Time Semantic Segmentation for AutonomousVehicles with Multi-Spectral Scenes
实时的利用可见光和红外数据集完成分割的网络（两个encoder分别输入可见光和红外图像，进行特征融合，一个decoder得到分割结果图）
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8206396&tag=1

9、Distilling Image Dehazing With Heterogeneous Task Imitation
利用自编码器（pixtopix）作为teacher网络，去教一个去雾网络（特色为残差空间通道注意力机制），teacher网络利用loss对student网络进行约束。
https://openaccess.thecvf.com/content_CVPR_2020/papers/Hong_Distilling_Image_Dehazing_With_Heterogeneous_Task_Imitation_CVPR_2020_paper.pdf

10、Taking A Closer Look at Domain Shift:Category-level Adversaries for Semantics Consistent Domain Adaptation
在domain adaptation中进行类别的特征对齐，对于类别加权
https://arxiv.org/pdf/1809.09478.pdf

11、DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
https://arxiv.org/pdf/1804.05827v1.pdf

12、Unsupervised object detection via LWIR/RGB translation
cycleGAN进行LWIR和RGB间的图像生成，并利用检测框的ROI区域进行L1 loss约束，对检测区域的loss约束进行加强。
https://openaccess.thecvf.com/content_CVPRW_2020/papers/w6/Abbott_Unsupervised_Object_Detection_via_LWIRRGB_Translation_CVPRW_2020_paper.pdf

13、FusionGAN: A generative adversarial network forinfrared and visible image fusion
利用GAN网络进行图像融合
https://www.researchgate.net/publication/327393843_FusionGAN_A_generative_adversarial_network_for_infrared_and_visible_image_fusion
14、Bidirectional Learning for Domain Adaptation of Semantic Segmentation
https://arxiv.org/pdf/1904.10620v1.pdf

15、ESL: Entropy-guided Self-supervised Learningfor Domain Adaptation in Semantic Segmentation
https://arxiv.org/pdf/2006.08658.pdf

16、Meta-DRN: Meta-Learning for 1-Shot ImageSegmentation
https://arxiv.org/pdf/2008.00247.pdf

17、Unsupervised Domain Adaptation for SemanticSegmentation via Class-Balanced Self-Training
https://openaccess.thecvf.com/content_ECCV_2018/papers/Yang_Zou_Unsupervised_Domain_Adaptation_ECCV_2018_paper.pdf

18、Multimodal Machine Learning: A Survey and Taxonomy
https://arxiv.org/pdf/1705.09406

19、A Survey on Semi-, Self- and Unsupervised Learning for Image Classification
https://arxiv.org/pdf/2002.08721v3.pdf

20、Image Segmentation Using Deep Learning: A Survey
https://arxiv.org/pdf/2001.05566.pdf

21、Unsupervised Domain Adaptation in Semantic Segmentation: a Review
https://arxiv.org/pdf/2005.10876.pdf

22、A survey of loss functions for semantic segmentation
https://arxiv.org/pdf/2006.14822.pdf

23、A Survey on Instance Segmentation: State of the art
https://arxiv.org/ftp/arxiv/papers/2007/2007.00047.pdf

24、Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
https://arxiv.org/pdf/2001.04074.pdf

25、Knowledge Distillation: A Survey
https://arxiv.org/pdf/2006.05525.pdf

26、Self-Supervised Learning for Stereo Matching with Self-Improving Ability
http://arxiv.org/pdf/1709.00930v1

27、Self-Supervised Co-Part Segmentation
https://arxiv.org/abs/1905.01298

28、Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation
https://arxiv.org/pdf/1911.01370.pdf

29、Mix-and-Match Tuning for Self-Supervised Semantic Segmentation
https://arxiv.org/pdf/1712.00661.pdf

30、A U-Net Based Discriminator for Generative Adversarial Networks
将判别器改为UNet型的网络
https://arxiv.org/pdf/2002.12655v1.pdf

31、DDcGAN: A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion
https://ieeexplore.ieee.org/document/9031751
fusiongan双判别器

32、VIFB: A Visible and Infrared Image Fusion Benchmark
https://arxiv.org/pdf/2002.03322v2.pdf
https://arxiv.org/abs/2002.03322
可见光和红外图像融合的benchmark

33、MFF-GAN: An unsupervised generative adversarial network with adaptive and gradient joint constraints for multi-focus image fusion
https://www.sciencedirect.com/science/article/pii/S1566253520303572

34、Infrared and visible image fusion based on target-enhanced multiscale transform decomposition
https://www.sciencedirect.com/science/article/pii/S0020025519308163
拉普拉斯金字塔图像融合

35、Infrared and visible image fusion via detail preserving adversarial learning
https://www.sciencedirect.com/science/article/pii/S1566253519300314
fusiongan加入感知loss和边缘增强loss

36、DRF: Disentangled Representation for Visible and Infrared Image Fusion
https://ieeexplore.ieee.org/document/9345717
scene表示和attribute表示两种特征空间融合

37、AttentionFGAN: Infrared and Visible Image Fusionusing Attention-based Generative AdversarialNetworks
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9103116&tag=1

38、ADVERSARIALLY LEARNED INFERENCE
https://arxiv.org/pdf/1606.00704.pdf

39、Multigrained Attention Network for Infrared and Visible Image Fusion
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9216075

40、MDLatLRR: A Novel Decomposition Method for Infrared and Visible Image Fusion
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9018389

41、A Generative Adversarial Network for Infrared and Visible Image Fusion Based on Semantic Segmentation
https://doaj.org/article/3cb33f7431e9479b8916bedc6600103b
将mask作为先验加入融合的GAN中

42、Infrared and Visible Image Fusion via Texture Conditional Generative Adversarial Network
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9335976

43、RFN-Nest: An end-to-end residual fusion network for infrared and visible images
https://arxiv.org/pdf/2103.04286.pdf

44、Image fusion based on generative adversarial network consistent with perception
https://www.sciencedirect.com/science/article/pii/S1566253521000439

45、Generalizing to Unseen Domains: A Survey on Domain Generalization
https://arxiv.org/abs/2103.03097v3

46、Scene Text Detection and Recognition: The Deep Learning Era
https://arxiv.org/pdf/1811.04256.pdf

47、FEANet: Feature-Enhanced Attention Network for RGB-Thermal
Real-time Semantic Segmentation
https://arxiv.org/abs/2110.08988