mlsanityData to 7 Oct 2026

MixUp-MIL: Novel Data Augmentation for Multiple Instance Learning and a Study on Thyroid Cancer Diagnosis

arXiv 2211.05862 ↗First posted 10 Nov 2022cs.CV cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Multiple instance learning exhibits a powerful approach for whole slide image-based diagnosis in the absence of pixel- or patch-level annotations. In spite of the huge size of hole slide images, the number of individual slides is often rather small, leading to a small number of labeled samples. To improve training, we propose and investigate different data augmentation strategies for multiple instance learning based on the idea of linear interpolations of feature vectors (known as MixUp). Based on state-of-the-art multiple instance learning architectures and two thyroid cancer data sets, an exhaustive study is conducted considering a range of common data augmentation strategies. Whereas a strategy based on to the original MixUp approach showed decreases in accuracy, the use of a novel intra-slide interpolation method led to consistent increases in accuracy.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 10 Nov 2022.

Builds on

16 of 21 references.

References · 16

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  3. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
  4. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
  5. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  6. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 254
  7. 2019Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathologycited by 172
  8. 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
  9. 2021TransMix: Attend to Mix for Vision Transformerscited by 79
  10. 2021Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classificationcited by 65
  11. 2020SuperMix: Supervising the Mixing Data Augmentationcited by 58
  12. 2020Weakly supervised multiple instance learning histopathological tumor segmentationcited by 46
4 more
  1. 2021Balanced-MixUp for Highly Imbalanced Medical Image Classificationcited by 46
  2. 2021A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learningcited by 19
  3. 2020Frozen-to-Paraffin: Categorization of Histological Frozen Sections by the Aid of Paraffin Sections and Generative Adversarial Networkscited by 4
  4. 2022Improving The Diagnosis of Thyroid Cancer by Machine Learning and Clinical Datacited by 4

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 3; 2025: 2.

9 papers.

  1. 2023CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Imagescited by 13
  2. 2024AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classificationcited by 10
  3. 2024Image Distillation for Safe Data Sharing in Histopathologycited by 6
  4. 2023AugDiff: Diffusion based Feature Augmentation for Multiple Instance Learning in Whole Slide Imagecited by 3
  5. 2023Slot-Mixup with Subsampling: A Simple Regularization for WSI Classificationcited by 3
  6. 2025Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learningcited by 2
  7. 2023MixUp-MIL: A Study on Linear & Multilinear Interpolation-Based Data Augmentation for Whole Slide Image Classificationcited by 1
  8. 2024Advancing Histopathology with Deep Learning Under Data Scarcity: A Decade in Reviewcited by 1
  9. 2025Contrastive Cross-Bag Augmentation for Multiple Instance Learning-based Whole Slide Image Classificationcited by 0