Vision-language models in remote sensing: Current progress and future trends
The remarkable achievements of ChatGPT and Generative Pre-trained Transformer 4 (GPT-
4) have sparked a wave of interest and research in the field of large language models …
4) have sparked a wave of interest and research in the field of large language models …
Unlocking the capabilities of explainable few-shot learning in remote sensing
Recent advancements have significantly improved the efficiency and effectiveness of deep
learning methods for image-based remote sensing tasks. However, the requirement for large …
learning methods for image-based remote sensing tasks. However, the requirement for large …
Few-shot object detection in remote sensing: Lifting the curse of incompletely annotated novel objects
Object detection (OD) is an essential and fundamental task in computer vision (CV) and
satellite image processing. Existing deep learning methods have achieved impressive …
satellite image processing. Existing deep learning methods have achieved impressive …
[HTML][HTML] Semi-supervised object detection with uncurated unlabeled data for remote sensing images
Annotating remote sensing images (RSIs) poses a significant challenge, primarily due to its
labor-intensive nature. Semi-supervised object detection (SSOD) methods address this …
labor-intensive nature. Semi-supervised object detection (SSOD) methods address this …
Zero-Shot Aerial Object Detection with Visual Description Regularization
Existing object detection models are mainly trained on large-scale labeled datasets.
However, annotating data for novel aerial object classes is expensive since it is time …
However, annotating data for novel aerial object classes is expensive since it is time …
Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery
The goal of this paper is to perform object detection in satellite imagery with only a few
examples thus enabling users to specify any object class with minimal annotation. To this …
examples thus enabling users to specify any object class with minimal annotation. To this …
Multistage enhancement network for tiny object detection in remote sensing images
With the rapid advances in deep learning techniques, remote sensing object detection
(RSOD) has achieved remarkable achievements in recent years. However, tiny object …
(RSOD) has achieved remarkable achievements in recent years. However, tiny object …
Few-Shot Object Detection with Multi-level Information Interaction for Optical Remote Sensing Images
Metalearning has been widely applied to solve the few-shot object detection (FSOD)
problem in natural scenes, which performs similarity measurement and information …
problem in natural scenes, which performs similarity measurement and information …
Segclip: Multimodal visual-language and prompt learning for high-resolution remote sensing semantic segmentation
S Zhang, B Zhang, Y Wu, H Zhou… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Remote sensing semantic segmentation is considered a key step in the intelligent
interpretation of high-resolution remote sensing (HRRS) images, with widespread …
interpretation of high-resolution remote sensing (HRRS) images, with widespread …
Unified multimodal fusion transformer for few shot object detection for remote sensing images
A Azeem, Z Li, A Siddique, Y Zhang, S Zhou - Information Fusion, 2024 - Elsevier
Object detection is a fundamental computer vision task with wide applications in remote
sensing, but traditional methods strongly rely on large annotated datasets which are difficult …
sensing, but traditional methods strongly rely on large annotated datasets which are difficult …