Image Segmentation

This repo was created for academic research and test result. Repo will update after academic article online.

This repo contains weights of Unet++ model with SE-ResNeXt101 encoder trained with our private Istanbul dataset and Inria and Massachusetts datasets seperately. Trainings have been realized using PyTorch and segmentation models library. We also provide an inference notebook to run prediction on GeoTiff images. This notebook also outputs prediction images as GeoTiff.

Weights Files

You can use the following links to download weights files:

Unet++ trained with Istanbul Dataset: Download
Unet++ trained with Inria Dataset: Download
Unet++ trained with Massachusetts Dataset: Download
Unet++ with InceptionResNetv2 encoder: Download
Unet++ with EfficientNet-b6 encoder: Download
UNet with SE-ResNeXt101 encoder: Download
UNet with InceptionResNetv2 encoder: Download
UNet with EfficientNet-b6 encoder: Download
DeepLabv3+ with SE-ResNeXt101 encoder:Download

Stack and Requirements

To run the notebook, following libraries are required:

torch == 1.7.1
segmentation-models-pytorch == 0.1.3
scikit-image = 0.18.1
GDAL == 3.2.1
tifffile == 2021.2.1

Image segmentation with private İstanbul Dataset

Related tags

Overview

Image Segmentation

Weights Files

Stack and Requirements

Owner

İrem KÖMÜRCÜ

People Interaction Graph

The codes and related files to reproduce the results for Image Similarity Challenge Track 1.

Implementation for "Conditional entropy minimization principle for learning domain invariant representation features"

(NeurIPS 2021) Pytorch implementation of paper "Re-ranking for image retrieval and transductive few-shot classification"

This repository is for EMNLP 2021 paper: It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data

Modelisation on galaxy evolution using PEGASE-HR

Code accompanying the paper "Wasserstein GAN"

An Open-Source Toolkit for Prompt-Learning.

SBINN: Systems-biology informed neural network

Public scripts, services, and configuration for running a smart home K3S network cluster

Python library containing BART query generation and BERT-based Siamese models for neural retrieval.

Implementation for Shape from Polarization for Complex Scenes in the Wild

A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis

3D AffordanceNet is a 3D point cloud benchmark consisting of 23k shapes from 23 semantic object categories, annotated with 56k affordance annotations and covering 18 visual affordance categories.

Information-Theoretic Multi-Objective Bayesian Optimization with Continuous Approximations

LWCC: A LightWeight Crowd Counting library for Python that includes several pretrained state-of-the-art models.

Rational Activation Functions - Replacing Padé Activation Units

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)

Trains an agent with stochastic policy gradient ascent to solve the Lunar Lander challenge from OpenAI

Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust.