Region Proposal
135 papers with code • 1 benchmarks • 5 datasets
Libraries
Use these libraries to find Region Proposal models and implementationsLatest papers with no code
Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery
Moreover, we study the performance of both visual and image-text features, namely DINOv2 and CLIP, including two CLIP models specifically tailored for remote sensing applications.
Debiased Novel Category Discovering and Localization
In recent years, object detection in deep learning has experienced rapid development.
CPN: Complementary Proposal Network for Unconstrained Text Detection
Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based.
Weakly Supervised Open-Vocabulary Object Detection
Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories within a single training dataset.
High-resolution power equipment recognition based on improved self-attention
The current trend of automating inspections at substations has sparked a surge in interest in the field of transformer image recognition.
Radar-Lidar Fusion for Object Detection by Designing Effective Convolution Networks
This underscores the value of radar-Lidar fusion in achieving precise object detection and localization, especially in challenging weather conditions.
Prompt-Driven Building Footprint Extraction in Aerial Images with Offset-Building Model
More accurate extraction of invisible building footprints from very-high-resolution (VHR) aerial images relies on roof segmentation and roof-to-footprint offset extraction.
Lung Diseases Image Segmentation using Faster R-CNNs
The regional proposal loss and classification loss assess model performance during training and classification phases.
What Makes Good Open-Vocabulary Detector: A Disassembling Perspective
A two-stage object detector includes a visual backbone, a region proposal network (RPN), and a region of interest (RoI) head.
Segmentation Framework for Heat Loss Identification in Thermal Images: Empowering Scottish Retrofitting and Thermographic Survey Companies
The objective of the framework is to au-tomatically identify, and crop heat loss sources caused by weak insulation, while also eliminating obstructive objects present in those images.