Weekly Editor's Picks | The Big Model Has Its Own MBTI Dataset, Chengdu University of Technology Builds SCDUNet++ Model for Landslide Mapping
Landslides are one of the most common natural disasters, usually triggered by earthquakes and rainfall. The damage caused by landslides triggered by earthquakes can sometimes be more serious than the damage caused by the earthquake itself.Chengdu University of Technology built the SCDUNet++ model for landslide mapping.To help prevent and control geological disasters.
This research case and its dataset can be viewed and downloaded on the hyper.ai official website.
From February 26 to March 1, hyper.ai official website updates:
* High-quality public datasets: 10
* AI4S paper cases: 3
* Popular encyclopedia entries: 10
Visit the official website:hyper.ai
Selected public datasets
1. SCDUNet++ landslide mapping dataset using multi-channel remote sensing data
This repository is the official implementation dataset of the paper: "Landslide Mapping Based on Hybrid CNN-Transformer Network and Deep Transfer Learning Using Remote Sensing Images with Topographic and Spectral Features SCDUNet++ Implementation".
Direct use:
https://hyper.ai/datasets/29647
2. PAWS-X paraphrase recognition cross-lingual adversarial dataset
The dataset contains 23,659 human-translated PAWS evaluation pairs and 296,406 machine-translated training pairs in 6 different languages: French, Spanish, German, Chinese, Japanese, and Korean. All translation pairs are derived from examples in the PAWS-Wiki.
Direct use:
https://hyper.ai/datasets/29264
3. CATSLU Chinese Audio Text Spoken Language Understanding Dataset
CATSLU is a Chinese voice +NLU A dialogue dataset for text understanding. This dataset comes from the first Chinese audio-text spoken language understanding challenge, including test datasets and results, training and validation datasets, baselines, and manuals.
Direct use:
https://hyper.ai/datasets/29764
4. Machine Mindset MBTI Machine Mindset Dataset
This dataset was proposed by the research team to train a large language model with different MBTI gender types. The release of this dataset has a unique contribution to the large language model (LLM) and the field of psychology.
Direct use:
https://hyper.ai/datasets/29692
5. Age Detection-Face Recognition Age Detection-Face Recognition Dataset
This dataset is a collection of images from people of different ages, it is specially designed for age prediction and face recognition tasks. This dataset contains different demographics, race, and gender.
Direct use:
https://hyper.ai/datasets/29695
6. Skin Types Dataset Oily, dry and normal skin type dataset
The dataset includes images of oily, dry, and normal skin types and can be used for classification and detection purposes.
Direct use:
https://hyper.ai/datasets/29718
7. AI-generated images vs. real images
The dataset is a collection of images from two different sources: web scraping and AI-generated content. The content covers multiple subjects: people, animals, portraits, and landscapes.
Direct use:
https://hyper.ai/datasets/29657
8. Example data from the paper "Deep learning system for predicting the progression of diabetic retinopathy"
This dataset is the sample data of the paper "Deep Learning System for Predicting the Progression Time of Diabetic Retinopathy", including the source data provided in the paper and a minimum dataset stored in Zenodo by the research team in order to replicate the algorithm code of the paper. This dataset is open for scientific research and non-commercial use.
Direct use:
https://hyper.ai/datasets/29716
9. 50 Types of Car Parts 50 types of car parts dataset
This is a dataset of 50 types of auto parts images. It includes training set, test set and validation set. The validation set and test set each have 5 images of 50 types. The image size is 224 X 224 X 3 and the format is .jpg. There are no augmented images in the dataset, all images are original images.
Direct use:
https://hyper.ai/datasets/29796
10. Popular Names By Birth Year 1880-2022 Popular names for people born in the United States between 1880 and 2022
This dataset contains the names, genders, and names of children born in the United States from 1880 to 2020. This dataset takes into account the child's birth year, gender, and popularity of naming a child in the United States.
Direct use:
https://hyper.ai/datasets/29784
For more updated datasets this week, please visit:
ScienceAI Selected Case Studies
Researchers from Chengdu University of Technology proposed a semantic segmentation model called SCDUNet++, which combines the advantages of convolutional neural networks (CNN) and Transformer to enhance the recognition and extraction of landslide features. Its performance is better than that of 8 other deep learning models such as FCN, DeepLabv3+, Segformer, etc. The results have been published in the International Journal of Applied Earth Observation and Geoinformation.
View the full report:
Shanghai Jiaotong University and Tsinghua University jointly built a diabetesRetinal complicationsThe early warning system DeepDR Plus can predict the progression of diabetic retinopathy within 5 years based solely on fundus images. The relevant results have been published in the journal "Nature".
View the full report:
The team from the Academy of Military Medical Sciences proposed a computational tool called MIDAS for mosaic integration of single-cell multimodal omics (scMulti-omics) data (i.e., different data sets only share some detection modalities) and knowledge transfer. Based on self-supervised learning and information-theoretic approaches, it first realized the integration functions of modality alignment, data completion, batch correction, etc. of general single-cell multimodal omics mosaic data, providing important original technology for building large-scale multi-omics cell maps and realizing large-scale single-cell multi-omics analysis and knowledge transfer. Related results have been published in "Nature Biotechnology"Journal.
View the full report:
Popular Encyclopedia Articles
1. Epoch
2. Class Boundary
3. Concept Drift
4. Transformer Model
5. Reproducing Kernel Hilbert Space
Here are hundreds of AI-related terms compiled to help you understand "artificial intelligence" here:
The above is all the content of this week’s editor’s selection. If you have resources that you want to include on the hyper.ai official website, you are also welcome to leave a message or submit an article to tell us!
See you next week!
About HyperAI
HyperAI (hyper.ai) is the leading artificial intelligence and high-performance computing community in China.We are committed to becoming the infrastructure in the field of data science in China and providing rich and high-quality public resources for domestic developers. So far, we have:
* Provide domestic accelerated download nodes for 1200+ public data sets
* Includes 300+ classic and popular online tutorials
* Interpretation of 100+ AI4Science paper cases
* Support 500+ related terms search
* Hosting the first complete Apache TVM Chinese documentation in China
Visit the official website to start your learning journey: