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 (28 $\times$ 28 or 28 $\times$ 28 $\times$ 28) medical samples and the corresponding expert annotations (class label). The existing baseline model (Google AutoML Vision, ResNet-50+3D) can reach an average accuracy of over 70\% on MedMNIST (v2) datasets, which is comparable to the performance of expert decision-making. Nevertheless, we note that there are two insurmountable obstacles to modeling on MedMNIST (v2): 1) the raw images are cropped to low scales may cause effective recognition information to be dropped and the classifier to have difficulty in tracing accurate decision boundaries; 2) the labelers' subjective insight may cause many uncertainties in the label space. To address these issues, we develop a Complex Mixer (C-Mixer) with a pre-training framework to alleviate the problem of insufficient information and uncertainty in the label space by introducing an incentive imaginary matrix and a self-supervised scheme with random masking. Our method (incentive learning and self-supervised learning with masking) shows surprising potential on both the standard MedMNIST (v2) dataset, the customized weakly supervised datasets, and other image enhancement tasks.

📄 PDF Abstract BibTeX arXiv:2304.10054

Code (0)

등록된 구현이 없습니다.

Tasks

AutoML Classification Decision Making Image Enhancement Self-Supervised Learning

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

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

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 repe…

Neighbor Embeddings Using Unbalanced Optimal Transport Metrics

2025-09-23 · Muhammad Rana, Keaton Hamm arxiv

This paper proposes the use of the Hellinger--Kantorovich metric from unbalanced optimal transport (UOT) in a dimensionality reduction and learning (supervised and unsupervised) pipeline. The performance of UOT is compar…

Dimensionality Reduction

MixerCA: An Efficient and Accurate Model for High-Performance Hyperspectral Image Classification

2026-04-28 · Mohammed Q. Alkhatib, Ali Jamali arxiv

Over the past decade, hyperspectral image (HSI) classification has drawn considerable interest due to HSIs' ability to effectively distinguish terrestrial objects by capturing detailed, continuous spectral information. T…

Hyperspectral Image Classification Semantic Segmentation