Calibrated Hyperspectral Image Reconstruction via Graph-based Self-Tuning Network.

Last update: Dec 29, 2022

Overview

mask-uncertainty-in-HSI

This repository contains the testing code and pre-trained models for the paper Calibrated Hyperspectral Image Reconstruction via Graph-based Self-Tuning Network.

Requirements

Python 3.7.10
Pytorch 1.9.1
Numpy 1.21.2
Scipy 1.7.1

Test

Ten simulation testing HSI (256x256x28) are provided. Testing trials can be determined by specify trial_num

To test a pre-trained model under miscalibration many-to-many, specify mode as many_to_many, last_train as 661.

To test a pre-trained model under miscalibration one-to-many, specify mode as one_to_many, last_train as 662.

To test a pre-trained model under traditional setting one-to-one, specify mode as one_to_one, last_train as 662.

Run

python test.py

Structure of directories

directory	description
`Data`	Ten simulation testing HSIs and two real masks for testing (256x256 and 660x660)
`test`	testing script
`utils`	utility functions
`tools`	model components
`ssim_torch`	function for computing SSIM
`many_to_many`	model structure and model checkpoint for miscalibration (many-to-many)
`one_to_many`	model structure and model checkpoint for miscalibration (one-to-many)
`one_to_one`	model structure and model checkpoint for traditional setting (one-to-one)

mask_uncertainty_spectral_SCI

Calibrated Hyperspectral Image Reconstruction via Graph-based Self-Tuning Network.

Related tags

Overview

mask-uncertainty-in-HSI

Requirements

Test

Structure of directories

mask_uncertainty_spectral_SCI

Owner

JIAMIAN WANG

Tensorflow 2 implementation of our high quality frame interpolation neural network

offical implement of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021

Understanding the Effects of Datasets Characteristics on Offline Reinforcement Learning

This repository is the official implementation of Using Time-Series Privileged Information for Provably Efficient Learning of Prediction Models

PyTorch Implementation of Sparse DETR

The Official PyTorch Implementation of "VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models" (ICLR 2021 spotlight paper)

Let Python optimize the best stop loss and take profits for your TradingView strategy.

Select, weight and analyze complex sample data

Deep Implicit Moving Least-Squares Functions for 3D Reconstruction

PyTorch implementation of "Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning"

Multitask Learning Strengthens Adversarial Robustness

Irrigation controller for Home Assistant

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

Code for "The Box Size Confidence Bias Harms Your Object Detector"

Wordplay, an artificial Intelligence based crossword puzzle solver.

Multiple-Object Tracking with Transformer

MARS: Learning Modality-Agnostic Representation for Scalable Cross-media Retrieva

Compositional Sketch Search

Code for "On Memorization in Probabilistic Deep Generative Models"

Finetune SSL models for MOS prediction