MPCM-Net: Multi-scale network integrates partial attention convolution with Mamba for ground-based cloud image segmentation
Niu, Penghui, She, Jiashuai, Cai, Taotao, Zhang, Yajuan, Zhang, Ping, Gu, Junhua, Li, Jianxin
–arXiv.org Artificial Intelligence
Ground-based cloud image segmentation is a critical research domain for photovoltaic power forecasting. Current deep learning approaches primarily focus on encoder-decoder architectural refinements. However, existing methodologies exhibit several limitations:(1)they rely on dilated convolutions for multi-scale context extraction, lacking the partial feature effectiveness and interoperability of inter-channel;(2)attention-based feature enhancement implementations neglect accuracy-throughput balance; and (3)the decoder modifications fail to establish global interdependencies among hierarchical local features, limiting inference efficiency. To address these challenges, we propose MPCM-Net, a Multi-scale network that integrates Partial attention Convolutions with Mamba architectures to enhance segmentation accuracy and computational efficiency. Specifically, the encoder incorporates MPAC, which comprises:(1)a MPC block with ParCM and ParSM that enables global spatial interaction across multi-scale cloud formations, and (2)a MPA block combining ParAM and ParSM to extract discriminative features with reduced computational complexity. On the decoder side, a M2B is employed to mitigate contextual loss through a SSHD that maintains linear complexity while enabling deep feature aggregation across spatial and scale dimensions. As a key contribution to the community, we also introduce and release a dataset CSRC, which is a clear-label, fine-grained segmentation benchmark designed to overcome the critical limitations of existing public datasets. Extensive experiments on CSRC demonstrate the superior performance of MPCM-Net over state-of-the-art methods, achieving an optimal balance between segmentation accuracy and inference speed. The dataset and source code will be available at https://github.com/she1110/CSRC.
arXiv.org Artificial Intelligence
Nov-18-2025
- Country:
- Asia
- China
- Beijing > Beijing (0.04)
- Hebei Province (0.04)
- Inner Mongolia (0.04)
- Jilin Province > Changchun (0.04)
- Shaanxi Province > Xi'an (0.04)
- Shanghai > Shanghai (0.04)
- Tianjin Province > Tianjin (0.05)
- Mongolia (0.04)
- Singapore (0.04)
- China
- Europe
- Austria (0.04)
- Germany > Bavaria
- Upper Bavaria > Munich (0.04)
- North America
- Canada
- British Columbia > Vancouver (0.04)
- Quebec > Montreal (0.04)
- Mexico > Gulf of Mexico (0.04)
- United States
- District of Columbia > Washington (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Maryland > Baltimore (0.04)
- Canada
- Oceania > Australia
- Queensland (0.04)
- Victoria > Melbourne (0.04)
- Western Australia > Joondalup (0.04)
- Asia
- Genre:
- Research Report > New Finding (0.67)
- Technology: