mlsanityData to 14 Oct 2026

Complex Mixer for MedMNIST Classification Decathlon

arXiv 2304.10054 ↗First posted 20 Apr 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

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 MedMNIST (v2). MedMNIST (v2) includes a large number of small-sized (28 × 28 or 28 × 28 × 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.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 20 Apr 2023.

Builds on

24 of 35 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2017Decoupled Weight Decay Regularizationcited by 1,831
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  6. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  7. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  8. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 727
  9. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  10. 2017Deep Learning for Medical Image Analysiscited by 401
  11. 2019AutoML: A Survey of the State-of-the-Artcited by 390
  12. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 339
12 more
  1. 2022Masked Siamese Networks for Label-Efficient Learningcited by 302
  2. 2017Deep Complex Networkscited by 217
  3. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 141
  4. 2017Medical Image Analysis using Convolutional Neural Networks: A Reviewcited by 99
  5. 2023MedViT: A Robust Vision Transformer for Generalized Medical Image Classificationcited by 89
  6. 2021S2-MLP: Spatial-Shift MLP Architecture for Visioncited by 83
  7. 2019Phase-aware Speech Enhancement with Deep Complex U-Netcited by 73
  8. 2022Positive-incentive Noisecited by 39
  9. 2022Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Searchcited by 38
  10. 2021Distribution-Free Federated Learning with Conformal Predictionscited by 16
  11. 2021GMLP: Building Scalable and Flexible Graph Neural Networks with Feature-Message Passingcited by 5
  12. 2022Deeply Supervised Layer Selective Attention Network: Towards Label-Efficient Learning for Medical Image Classificationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 1; 2026: 3.

6 papers.

  1. 2025Manifold Topological Deep Learning for Biomedical Datacited by 4
  2. 2023Medi-CAT: Contrastive Adversarial Training for Medical Image Classificationcited by 2
  3. 2024Resource-efficient Medical Image Analysis with Self-adapting Forward-Forward Networkscited by 2
  4. 2026G-LoG Bi-filtration for Medical Image Classificationcited by 0
  5. 2026Deep neural networks with Fisher vector encoding for medical image classificationcited by 0
  6. 2026Combinatorial Network-Based Manifold Topological Deep Learning for Image Analysiscited by 0