paper-with-me

홈 › Papers

RSRWKV: A Linear-Complexity 2D Attention Mechanism for Efficient Remote Sensing Vision Task

2025-03-26 · Chunshan Li, Rong Wang, Xiaofei Yang, Dianhui Chu

High-resolution remote sensing analysis faces challenges in global context modeling due to scene complexity and scale diversity. While CNNs excel at local feature extraction via parameter sharing, their fixed receptive fields fundamentally restrict long-range dependency modeling. Vision Transformers (ViTs) effectively capture global semantic relationships through self-attention mechanisms but suffer from quadratic computational complexity relative to image resolution, creating critical efficiency bottlenecks for high-resolution imagery. The RWKV model's linear-complexity sequence modeling achieves breakthroughs in NLP but exhibits anisotropic limitations in vision tasks due to its 1D scanning mechanism. To address these challenges, we propose RSRWKV, featuring a novel 2D-WKV scanning mechanism that bridges sequential processing and 2D spatial reasoning while maintaining linear complexity. This enables isotropic context aggregation across multiple directions. The MVC-Shift module enhances multi-scale receptive field coverage, while the ECA module strengthens cross-channel feature interaction and semantic saliency modeling. Experimental results demonstrate RSRWKV's superior performance over CNN and Transformer baselines in classification, detection, and segmentation tasks on NWPU RESISC45, VHR-10.v2, and GLH-Water datasets, offering a scalable solution for high-resolution remote sensing analysis.

📄 PDF Abstract BibTeX arXiv:2503.20382

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial Reasoning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Residual Connection 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Multiattention network for semantic segmentation of fine-resolution remote sensing images

2021-05-15 · IEEE Transactions on Geoscience and Remote Sensing 2021 5 · Rui Li, Shunyi Zheng, Ce Zhang, Chenxi Duan 외

Semantic segmentation of remote sensing images plays an important role in a wide range of applications, including land resource management, biosphere monitoring, and urban planning. Although the accuracy of semantic segm…

ManagementSegmentationSemantic Segmentation

Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images

2020-09-03 · Rui Li, Shunyi Zheng, Chenxi Duan, Ce Zhang 외

Semantic segmentation of remote sensing images plays an important role in a wide range of applications including land resource management, biosphere monitoring and urban planning. Although the accuracy of semantic segmen…

ManagementSegmentationSemantic Segmentation

Less is More: AMBER-AFNO -- a New Benchmark for Lightweight 3D Medical Image Segmentation

2025-08-03 · Andrea Dosi, Semanto Mondal, Rajib Chandra Ghosh, Massimo Brescia 외 arxiv

We adapt the remote sensing-inspired AMBER model from multi-band image segmentation to 3D medical datacube segmentation. To address the computational bottleneck of the volumetric transformer, we propose the AMBER-AFNO ar…

Medical Image Segmentation

HIMOSA: Efficient Remote Sensing Image Super-Resolution with Hierarchical Mixture of Sparse Attention

2025-11-29 · Yi Liu, Yi Wan, Xinyi Liu, Qiong Wu 외 arxiv

In remote sensing applications, such as disaster detection and response, real-time efficiency and model lightweighting are of critical importance. Consequently, existing remote sensing image super-resolution methods ofte…

Computational EfficiencyImage Super-Resolution

A Lightweight Sparse Focus Transformer for Remote Sensing Image Change Captioning

2024-05-10 · Dongwei Sun, Yajie Bao, Junmin Liu, Xiangyong Cao

Remote sensing image change captioning (RSICC) aims to automatically generate sentences that describe content differences in remote sensing bitemporal images. Recently, attention-based transformers have become a prevalen…

Decoder