gap-filling for remote-sensing data

Implementation of 2D and 3D U-Net architecture for Semantic Segmentation of brain tumor on BraTS'19 Dataset

MultiPass U-Net is an advanced image segmentation model designed to iteratively refine predictions by running multiple passes through a U-Net architecture. Ideal for histopathology and medical imaging, it improves segmentation of fine structures and rare features by leveraging deep contextual learning across passes.

Iterative Vertebrae Segmentation - VerSe dataset

Find the nuclei in divergent images to using UNet

This repository implements U-Net for image segmentation on a self-driving car dataset, covering data preprocessing, training, and evaluation.

Machine Learning

Tensorflow based framework for 3D-Unet with Knowledge Distillation

The project aims to transform the realm of beauty by developing a sophisticated UNet architecture model where the input represents a woman adorned with makeup, while the output showcases her natural, makeup-free beauty.

Collection of notebooks for image segmentation tasks.

Tensorflow implementation of UNet on surgical Instrument dataset from laparoscopic videos

A U-Net-based deep learning ensemble model for wildebeest-sized animal detection from satellite imagery. A version used for the paper accepted by Nature Communications: "Deep learning enables satellite-based monitoring of large populations of terrestrial mammals across heterogeneous landscape" (https://rdcu.be/dc8bU).

Breast cancer is one of the most common causes of death among women worldwide. Early detection helps reduce the number of premature deaths. In the study, I am working on creating a convolutional neural network capable of identifying tumor areas within medical images (which were taken with ultrasound).

People with pulmonary disease often have a high opacity, which makes segmentation of the lung from chest X-rays more difficult. In this study, I propose a methodology to improve the performance of the U-NET structure so that it is able to extract the features and spatial characteristics of the X-ray images of the chest region.

In this project, we analyzed a video recording of a vehicle driving on the road and computed semantic segmentation for each frame in the video.

A computer vision project (image segmentation project) which aims to remove texts on images using Unet model. Tensorflow 2 is used as a ML library.

Semantic Segmentation project for Autonomous Driving based on a TensorFlow implementation of UNet

Unet-based semantic segmentation for pet images in TensorFlow using the Oxford-IIIT Pet Dataset.

Image segmentation using U-Net in tensorflow

TensorFlow Lite segmentation on Raspberry Pi 4 aka Unet at 4.2 FPS