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

Seg-Torch for Image Segmentation with Torch

[CVPR 2022] Structured Sparse R-CNN for Direct Scene Graph Generation

TeST: Temporal-Stable Thresholding for Semi-supervised Learning

Code for NeurIPS2021 submission "A Surrogate Objective Framework for Prediction+Programming with Soft Constraints"

Deep Learning and Logical Reasoning from Data and Knowledge

Code to accompany the paper "Finding Bipartite Components in Hypergraphs", which is published in NeurIPS'21.

ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhin et al., 2020).

Code for the paper "Graph Attention Tracking". (CVPR2021)

SLAMP: Stochastic Latent Appearance and Motion Prediction

ServiceX Transformer that converts flat ROOT ntuples into columnwise data

Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks.

Autoregressive Predictive Coding: An unsupervised autoregressive model for speech representation learning

Source code for "Progressive Transformers for End-to-End Sign Language Production" (ECCV 2020)

[ICCV2021] 3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds

On Generating Extended Summaries of Long Documents

Code for our paper "MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction" published at ICCV 2021.

Spatio-Temporal Entropy Model (STEM) for end-to-end leaned video compression.

A tight inclusion function for continuous collision detection

tensorflow implementation of 'YOLO : Real-Time Object Detection'

Process text, including tokenizing and representing sentences as vectors and Applying some concepts like RNN, LSTM and GRU to create a classifier can detect the language in which a sentence is written from among 17 languages.