Python code for the paper How to scale hyperparameters for quickshift image segmentation

Last update: Jan 25, 2022

Related tags

Overview

How to scale hyperparameters for quickshift image segmentation

Python code for the paper How to scale hyperparameters for quickshift image segmentation

There is nothing to install, one simply has to run the scripts. Some experiments require to download data (additional details are given in the scripts).

Disclaimer

The code was tested with version 0.18.2 of skimage, using another version may lead to unexplained behaviors.

General Organization

The main scripts producing the results and plotting are in the root directory:

compute_evolution.py: raw results for the evolution of the number of local maxima and number of superpixels as a function of the image size.
plot_evolution.py: plotting the evolution of the number of superpixels as a function of the image size
get_segmentations.py: computs segmentations with quickshift and storing the results
size_scaling.py: scaling with respect to the size of the images on real data
hyperparameter_scaling.py: scaling with respect to the hyperparameters on real data

Auxilliary functions are collected in the utils folder.

Python code for the paper How to scale hyperparameters for quickshift image segmentation

Related tags

Overview

How to scale hyperparameters for quickshift image segmentation

Disclaimer

General Organization

Owner

Library for 8-bit optimizers and quantization routines.

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

Code for ICMI2020 and ICMI2021 papers: "Studying Person-Specific Pointing and Gaze Behavior for Multimodal Referencing of Outside Objects from a Moving Vehicle" and "ML-PersRef: A Machine Learning-based Personalized Multimodal Fusion Approach for Referencing Outside Objects From a Moving Vehicle"

Iran Open Source Hackathon

Semantic code search implementation using Tensorflow framework and the source code data from the CodeSearchNet project

Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation

Repo for parser tensorflow(.pb) and tflite(.tflite)

Official code release for 3DV 2021 paper Human Performance Capture from Monocular Video in the Wild.

A task-agnostic vision-language architecture as a step towards General Purpose Vision

Hierarchical-Bayesian-Defense - Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference (Openreview)

Revisiting Global Statistics Aggregation for Improving Image Restoration

A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

Code for the CIKM 2019 paper "DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting".

CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching（CVPR2021）

Official implementation of "SinIR: Efficient General Image Manipulation with Single Image Reconstruction" (ICML 2021)

Dahua Camera and Doorbell Home Assistant Integration

A library for performing coverage guided fuzzing of neural networks

Improving Convolutional Networks via Attention Transfer (ICLR 2017)

Developing your First ML Workflow of the AWS Machine Learning Engineer Nanodegree Program

This is a virtual picture dragging application. Users may virtually slide photos across the screen. The distance between the index and middle fingers determines the movement. Smaller distances indicate click and motion, whereas bigger distances indicate only hand movement.