Quantitative causality, causality-guided scientific discovery, and causal machine learning

no code implementations • 20 Feb 2024 • X. San Liang, Dake Chen, Renhe Zhang

It has been said, arguably, that causality analysis should pave a promising way to interpretable deep learning and generalization.

LSRFormer: Efficient Transformer Supply Convolutional Neural Networks with Global Information for Aerial Image Segmentation

1 code implementation • IEEE Transactions on Geoscience and Remote Sensing 2024 • Renhe Zhang, Qian Zhang, Guixu Zhang

Convolutional Neural Networks (CNNs) can capture local context information well but cannot model the global dependencies.

Image Segmentation Semantic Segmentation

DSAT-Net: Dual Spatial Attention Transformer for Building Extraction from Aerial Images

1 code implementation • IEEE Geoscience and Remote Sensing Letters 2023 • Renhe Zhang, Zhechun Wan, Qian Zhang, Guixu Zhang

The local attention path (LAP) uses efficient stripe convolution to generate local attention, which can alleviate the loss of information caused by down-sampling operation in the GAP and supplement the spatial details.

Extracting Buildings In Remote Sensing Images Semantic Segmentation

SDSC-UNet: Dual Skip Connection ViT-based U-shaped Model for Building Extraction

1 code implementation • IEEE Geoscience and Remote Sensing Letters 2023 • Renhe Zhang, Qian Zhang, Guixu Zhang

Furthermore, unlike the previous single-skip-connection structure of U-shaped methods, we build a novel dual skip connection structure inside the model.

Decoder Extracting Buildings In Remote Sensing Images +1