Picture for Shenghui Fang

Shenghui Fang

MetaSegNet: Metadata-collaborative Vision-Language Representation Learning for Semantic Segmentation of Remote Sensing Images

Add code
Dec 20, 2023
Viaarxiv icon

Efficient Hybrid Transformer: Learning Global-local Context for Urban Scene Segmentation

Add code
Oct 13, 2021
Figure 1 for Efficient Hybrid Transformer: Learning Global-local Context for Urban Scene Segmentation
Figure 2 for Efficient Hybrid Transformer: Learning Global-local Context for Urban Scene Segmentation
Figure 3 for Efficient Hybrid Transformer: Learning Global-local Context for Urban Scene Segmentation
Figure 4 for Efficient Hybrid Transformer: Learning Global-local Context for Urban Scene Segmentation
Viaarxiv icon

A Novel Transformer based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images

Add code
May 11, 2021
Figure 1 for A Novel Transformer based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images
Figure 2 for A Novel Transformer based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images
Viaarxiv icon

SaNet: Scale-aware Neural Network for Semantic Labelling of Multiple Spatial Resolution Aerial Images

Add code
Apr 10, 2021
Figure 1 for SaNet: Scale-aware Neural Network for Semantic Labelling of Multiple Spatial Resolution Aerial Images
Figure 2 for SaNet: Scale-aware Neural Network for Semantic Labelling of Multiple Spatial Resolution Aerial Images
Figure 3 for SaNet: Scale-aware Neural Network for Semantic Labelling of Multiple Spatial Resolution Aerial Images
Figure 4 for SaNet: Scale-aware Neural Network for Semantic Labelling of Multiple Spatial Resolution Aerial Images
Viaarxiv icon