Picture for Gui-Song Xia

Gui-Song Xia

Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

Add code
May 09, 2024
Viaarxiv icon

Dual Relation Mining Network for Zero-Shot Learning

May 06, 2024
Figure 1 for Dual Relation Mining Network for Zero-Shot Learning
Figure 2 for Dual Relation Mining Network for Zero-Shot Learning
Figure 3 for Dual Relation Mining Network for Zero-Shot Learning
Figure 4 for Dual Relation Mining Network for Zero-Shot Learning
Viaarxiv icon

Anchor-based Robust Finetuning of Vision-Language Models

Apr 09, 2024
Figure 1 for Anchor-based Robust Finetuning of Vision-Language Models
Figure 2 for Anchor-based Robust Finetuning of Vision-Language Models
Figure 3 for Anchor-based Robust Finetuning of Vision-Language Models
Figure 4 for Anchor-based Robust Finetuning of Vision-Language Models
Viaarxiv icon

3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions

Add code
Apr 07, 2024
Viaarxiv icon

H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model

Add code
Mar 29, 2024
Figure 1 for H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model
Figure 2 for H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model
Figure 3 for H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model
Figure 4 for H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model
Viaarxiv icon

Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization

Add code
Mar 21, 2024
Figure 1 for Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization
Figure 2 for Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization
Figure 3 for Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization
Figure 4 for Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization
Viaarxiv icon

Learning Cross-view Visual Geo-localization without Ground Truth

Mar 19, 2024
Figure 1 for Learning Cross-view Visual Geo-localization without Ground Truth
Figure 2 for Learning Cross-view Visual Geo-localization without Ground Truth
Figure 3 for Learning Cross-view Visual Geo-localization without Ground Truth
Figure 4 for Learning Cross-view Visual Geo-localization without Ground Truth
Viaarxiv icon

Few-Shot Learning for Annotation-Efficient Nucleus Instance Segmentation

Feb 28, 2024
Viaarxiv icon

GOOD: Towards Domain Generalized Orientated Object Detection

Add code
Feb 20, 2024
Viaarxiv icon

HiCD: Change Detection in Quality-Varied Images via Hierarchical Correlation Distillation

Add code
Jan 19, 2024
Viaarxiv icon