Official PyTorch implementation of Revisiting Image Pyramid Structure for High Resolution Salient Object Detection (ACCV 2022)

Official implementation of ResUNet++, CRF, and TTA for segmentation of medical images (IEEE JBIHI)

Mask R-CNN, FPN, LinkNet, PSPNet and UNet with multiple backbone architectures support readily available

Deep Extreme Cut http://www.vision.ee.ethz.ch/~cvlsegmentation/dextr . a tool to do automatically object segmentation from extreme points.

This is a python implementation of Hierarchical Image Matting Model for Segmentation.

This repo contains a UNet based deep learning model for identifying roads from aerial images

This repository contains the Jupyter Notebook for the UNet-VGG16 CNN Model trained on the Lunar Landscape Images Dataset.

This project uses MRF (Markov Random Field) to remove noise from the image and segment it.

This repository contains an implementation of image segmentation using PyTorch and the U-Net architecture. The project focuses on human segmentation using the EfficientNet-B0 encoder and custom training pipeline.

A codebase for 2 projects of Signal Processing course.

Kaggle Competition: Airbus Ship Detection Challenge

TGSSalt_Identification_Kaggle_Challenge https://www.kaggle.com/c/tgs-salt-identification-challenge

This repository contains tasks focusing on prompt engineering for vision models. Each task explores different aspects of image segmentation, object detection, and image generation using advanced machine learning models. Below are detailed descriptions of the tasks and their respective notebooks.

A retinal segmentation model without learning algorithm