Dual-Perspective United Transformer for Object Segmentation in Optical Remote Sensing Images
This addresses segmentation challenges in remote sensing, which is important for applications like environmental monitoring, but appears incremental as it builds on existing Transformer and convolutional approaches.
The paper tackles the problem of object segmentation in optical remote sensing images by proposing a Dual-Perspective United Transformer (DPU-Former) that integrates long-range dependencies and spatial details, outperforming state-of-the-art methods on multiple datasets.
Automatically segmenting objects from optical remote sensing images (ORSIs) is an important task. Most existing models are primarily based on either convolutional or Transformer features, each offering distinct advantages. Exploiting both advantages is valuable research, but it presents several challenges, including the heterogeneity between the two types of features, high complexity, and large parameters of the model. However, these issues are often overlooked in existing the ORSIs methods, causing sub-optimal segmentation. For that, we propose a novel Dual-Perspective United Transformer (DPU-Former) with a unique structure designed to simultaneously integrate long-range dependencies and spatial details. In particular, we design the global-local mixed attention, which captures diverse information through two perspectives and introduces a Fourier-space merging strategy to obviate deviations for efficient fusion. Furthermore, we present a gated linear feed-forward network to increase the expressive ability. Additionally, we construct a DPU-Former decoder to aggregate and strength features at different layers. Consequently, the DPU-Former model outperforms the state-of-the-art methods on multiple datasets. Code: https://github.com/CSYSI/DPU-Former.