GitHub

T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

Note: This model has been trained for approximately 2.7M steps (batch size = 1) and is still in the training process. I have attached a .ipynb file in the repository. You can refer to it to know how ...
IEEE

Look Twice and Closer: A Coarse-to-Fine Segmentation Network for Small Objects in Remote Sensing Images

Abstract: Convolutional neural networks (CNNs) are frequently used to analyze remote sensing images and achieve impressive progress. Limited by the receptive field size of CNNs, small objects tended ...
IEEE

Variance Stabilized Loss Function for Semantic Segmentation of Smaller Objects in Medical Images

Abstract: Accurate segmentation in medical images is a crucial step in a CAD system, improving clinical workflows and proper treatment planning. Deep learning-based approaches have gained popularity ...
GitHub

Mask R-CNN Instance Segmentation with OpenCV

This project demonstrates instance segmentation using Mask R-CNN with the OpenCV DNN module. The model is pre-trained on the COCO dataset and can detect and segment multiple object classes in images.