GRSL 2023： Attention-Aware Three-Branch Network for Salient Object Detection in Remote Sensing Images
基于encoder-decoder框架，提出了一系列缝合模块，GCA，FDUC，MSDC，RA。
GRSL 2023：ORSI Salient Object Detection via Cross-Scale Interaction and Enlarged Receptive Field
基于encoder-decoder框架，提出了三个缝合性模块，GLM，FSCM，EIM。
GLM：论文中没有给出图例，根据论文，GLM是基于通道维度的GAP和GMP对f5特征进行重新加权
FSCM：基于残差连接和dilation卷积，还有spatial attention，对特征进行润色
EIM：基于多尺度特征和空间，通道注意力，对特征进行润色
ISPRS 2023：Global–local–global context-aware network for salient object detection in optical remote sensing images
提出了GLGCNet，基于encoder-decoder框架，包含两个创新性模块，saliency-up module和edge assignment module，奇淫技巧堆模块无营养。
JSTARS 2023：An Important Pick-and-Pass Gated Refinement Network for Salient Object Detection in Optical Remote Sensing Images
奇淫技巧，堆模块
JSTARS 2023： Semantic-Edge Interactive Network for Salient Object Detection in Optical Remote Sensing Images
奇淫技巧，堆模块，毫无意义
TCSVT 2023：Edge and Skeleton Guidance Network for Salient Object Detection in Optical Remote Sensing Images
分为两个阶段训练，第一个阶段，三个任务损失监督，saliency map，edge map，Skeleton map
第二个阶段，根据第一阶段的预测，进行融合，学习一个最终的saliency map
堆模块，SGA，MIF
TGRS 2023：Adaptive Edge-Aware Semantic Interaction Network for Salient Object Detection in Optical Remote Sensing Images
堆模块，LDAM，MFEM，DSIM
Local Detail Aggregation Module (LDAM)：通过CA，SA，average pooling，max pooling得到融合特征
Multiscale Feature Extraction Module (MFEM)：通过不同的dilation conv多尺度的特征进行提取，得到联合特征
Deep Semantic Interaction Module (DSIM)：该模块通过一种专门设计的图投影方法，将特征图转换为图结构，并通过三个并行的图卷积分支进行深度语义推理，从而能够从语义角度准确识别显著目标。
TGRS 2023：Adaptive Spatial Tokenization Transformer for Salient Object Detection in Optical Remote Sensing Images
a novel dynamic spatial tokenization transformer
a specific dense token aggregation decoder (DTAD) is proposed
adaptive spatial tokenization module (ASTM),
TGRS 2023：Boundary-Aware Network With Two-Stage Partial Decoders for Salient Object Detection in Remote Sensing Images
提出了一个BANet，包含两个decoder，一个监督saliency map，一个监督contour map
堆模块，提出了一个RMS模块，采用多尺度卷积核对一个特征进行多尺度的聚合
堆模块，提出了一个MFA模块，对三个尺度的特征进行上采样和解码融合
TGRS 2023：Boundary-Semantic Collaborative Guidance Network With Dual-Stream Feedback Mechanism for Salient Object Detection in Optical Remote Sensing Imagery
propose a novel BSCGNet dedicated to ORSI-SOD
a boundary protection calibration (BPC) module for the encoder,
the dual feature feedback complementary (DFFC) module
the adaptive feedback refinement (AFR) module
https://github.com/YUHsss/BSCGNet
奇淫技巧，堆模块，毫无意义
TGRS 2023：CRNet: Channel-Enhanced Remodeling-Based Network for Salient Object Detection in Optical Remote Sensing Images
CEM：channel enhance module
RFM：redefined feature module
奇淫技巧，堆模块，毫无意义
TGRS 2023：Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment
奇淫技巧，堆模块，毫无意义
TGRS 2023：ORSI Salient Object Detection via Bidimensional Attention and Full-Stage Semantic Guidance
奇淫技巧，堆模块，毫无意义
TGRS 2023：Progressive Context-Aware Dynamic Network for Salient Object Detection in Optical Remote Sensing Images
Dynamic Filtering Networks：卷积核的kernel参数根据input的特征学习生成
[32] B. D. Brabandere, X. Jia, T. Tuytelaars, and L. Van Gool, “Dynamic filter networks,” in Proc. Adv. Neural Inform. Process. Syst., 2016, pp. 1–14.
[33] J. He, Z. Deng, and Y. Qiao, “Dynamic multi-scale filters for semantic segmentation,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct. 2019, pp. 3561–3571.
[34] Y. Pang, L. Zhang, X. Zhao, and H. Lu, “Hierarchical dynamic filtering network for RGB-D salient object detection,” in Proc. Eur. Conf. Comput. Vis., A. Vedaldi, H. Bischof, T. Brox, and J.-M. Frahm, Eds. Cham, Switzerland: Springer, 2020, pp. 235–252.
[42] M. Zhang et al., “Dynamic context-sensitive filtering network for video salient object detection,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct. 2021, pp. 1533–1543.
[43] Y. Nirkin, L. Wolf, and T. Hassner, “HyperSeg: Patch-wise hypernetwork for real-time semantic segmentation,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2021, pp. 4060–4069.
[44] B. Zhang, Y. liu, Z. Tian, and C. Shen, “Dynamic neural representational decoders for high-resolution semantic segmentation,” in Proc. Adv. Neural Inform. Process. Syst., 2021, pp. 17388–17399.
TIP 2023：Salient Object Detection in Optical Remote Sensing Images Driven by Transformer
https://github.com/MathLee/GeleNet
propose a transformer-based ORSI-SOD solution, GeleNet, with the global-to-local paradigm
propose the D-SWSAM and its variant SWSAM to enhance local interactions of the extracted global feature embeddings.
propose the KTM to enhance contextual interactions of two middle-level features
ESWA 2024：MEANet: An effective and lightweight solution for salient object detection in optical remote sensing images
灌水两个模块，MEA，MSG
Multiscale edge-embedded attention module （MEA）
Multilevel semantic guidance module （MSG）
GRSL 2024：Global–Local Semantic Interaction Network for Salient Object Detection in Optical Remote Sensing Images With Scribble Supervision
propose a high-performance yet cost-effective RSI-SOD method, the global-local semantic interaction network (GLSIN), utilizing an encoder-decoder architecture. In the encoder, we synergize the Transformer with CNN to design a Dual Branch Encoder, capturing both global semantic information and local spatial details within images.
propose the global-local affinity block (GLAB) to facilitate effective information interaction and the flexible multiscale polishing gate (FMPG) to further enhance salient features.
In the decoder, we construct a Feature Shrinkage Decoder incorporating the global-local fusion block (GLFB).
奇淫技巧，堆模块
弱监督 scribble 学习：This includes applying partial cross-entropy lossPCE to the saliency map and integrating a gated structure-aware lossGSA [16] as an auxiliary component, focusing the model on salient object structures.
[16] J. Zhang, X. Yu, A. Li, P. Song, B. Liu, and Y. Dai, “Weakly-supervised salient object detection via scribble annotations,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2020, pp. 12546–12555.
TGRS 2024：United Domain Cognition Network for Salient Object Detection in Optical Remote Sensing Images
