This repository contains our work on ensembling in semantic image segmentation as part of the Google Research Kaggle competition "Identify Contrails to Reduce Global Warming".

Code Implementation of the article "A Framework for Real-Time Volcano-Seismic Event Recognition Based on Multi-Station Seismograms and Semantic Segmentation Models" (under review).

Use DeeplabV3+ to segment the flexor tendon, median nerve, and carpal tunnel separately from MR images.

This repo hosts the water body extraction from satellite images using DeeplabV3+ model.

This project extends support for DeepLabV3+ implementation on TensorFlow with multiple backbones, including: ResNet50/101/V2, DenseNet121/169, MobileNet/V2, and VGG16/19.

minimal-segmentation

DeepLab v3+ and Floral-Net, a U-Net inspired CNN, for segmenting flowers and backgrounds in the Oxford Flower Dataset, enhancing accuracy through tailored architecture and class imbalance handling.

Fine-tune and evaluate deep learning models built with PyTorch for semantic segmentation of trees from satellite imagery of forestry areas.

Implementation of state-of-the-art models to do segmentation over our own dataset.

百度车道线比赛

Image segmentation using deeplab

3rd place solution of Seismic Facies Identification Challenge

A Tensorflow implementation of Deeplabv3+ trained on VOC2012.

I am aiming to write different Semantic Segmentation models from scratch with different pretrained backbones.

Source code for "Amodal Instance Segmentation and Multi-Object Tracking with Deep Pixel Embedding"

Monocular Depth Estimation via a Fully Convolutional Deep Neural Network, utilising Atrous Convolutions, with 3D Point Cloud Visualisation.

PyTorch Implementation of Semantic Segmentation CNNs: This repository features key architectures like UNet, DeepLabv3+, SegNet, FCN, and PSPNet. It's crafted to provide a solid foundation for Semantic Segmentation tasks using PyTorch.

Tensorflow-Keras semantic segmentation

In search of effective and efficient Pipeline for Distillating Knowledge in Convolutional Neural Networks