Benchmarking PNW Model for MedMNIST to 100% Accuracy

2026-04-20 · Bo Deng arxiv

In this paper, we introduce a new concept called Artificial Special Intelligence by which Machine Learning models for the classification problem can be trained error-free, thus acquiring the capability of not making repeated mistakes. The method is applied to 18 MedMNIST biomedical datasets. Except for three datasets, which suffer from the double-labeling problem, all are trained to perfection.

📄 PDF Abstract BibTeX arXiv:2604.18916

Code (0)

등록된 구현이 없습니다.

Complex Mixer for MedMNIST Classification Decathlon

2023-04-20 · Zhuoran Zheng, Xiuyi Jia

With the development of the medical image field, researchers seek to develop a class of datasets to block the need for medical knowledge, such as \text{MedMNIST} (v2). MedMNIST (v2) includes a large number of small-sized…

AutoML Classification Decision Making Image Enhancement+1

MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis

2020-10-28 · Jiancheng Yang, Rui Shi, Bingbing Ni

We present MedMNIST, a collection of 10 pre-processed medical open datasets. MedMNIST is standardized to perform classification tasks on lightweight 28x28 images, which requires no background knowledge. Covering the prim…

AutoML General Classification Medical Image Analysis regression

Benchmarking MedMNIST dataset on real quantum hardware

2025-02-18 · Gurinder Singh, Hongni Jin, Kenneth M. Merz Jr

Quantum machine learning (QML) has emerged as a promising domain to leverage the computational capabilities of quantum systems to solve complex classification tasks. In this work, we present the first comprehensive QML s…

Benchmarking image-classification Image Classification Medical Image Classification+1

MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification

2021-10-27 · Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu 외

We introduce MedMNIST v2, a large-scale MNIST-like dataset collection of standardized biomedical images, including 12 datasets for 2D and 6 datasets for 3D. All images are pre-processed into a small size of 28x28 (2D) or…

AutoML image-classification Image Classification

Useful nonrobust features are ubiquitous in biomedical images

2026-04-24 · Coenraad Mouton, Randle Rabe, Niklas C. Koser, Nicolai Krekiehn 외 arxiv

We study whether deep networks for medical imaging learn useful nonrobust features - predictive input patterns that are not human interpretable and highly susceptible to small adversarial perturbations - and how these fe…