mlsanityData to 14 Oct 2026

Jigsaw Regularization in Whole-Slide Image Classification

arXiv 2603.20386 ↗First posted 20 Mar 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Computational pathology involves the digitization of stained tissues into whole-slide images (WSIs) that contain billions of pixels arranged as contiguous patches. Statistical analysis of WSIs largely focuses on classification via multiple instance learning (MIL), in which slide-level labels are inferred from unlabeled patches. Most MIL methods treat patches as exchangeable, overlooking the rich spatial and topological structure that underlies tissue images. This work builds on recent graph-based methods that aim to incorporate spatial awareness into MIL. Our approach is new in two regards: (1) we deploy vision foundation-model embeddings to incorporate local spatial structure within each patch, and (2) achieve across-patch spatial awareness using graph neural networks together with a novel em jigsaw regularization. We find that a combination of these two features markedly improves classification over state-of-the-art attention-based MIL approaches on benchmark datasets in breast, head-and-neck, and colon cancer.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 45 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

21 of 45 references.

References · 21

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  8. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  9. 2018Deep Graph Infomaxcited by 1,106
  10. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  11. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  12. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
9 more
  1. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  2. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 375
  3. 2021Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networkscited by 124
  4. 2020Rethinking pooling in graph neural networkscited by 73
  5. 2021Hierarchical Graph Representations in Digital Pathologycited by 59
  6. 2020Representation Learning of Histopathology Images using Graph Neural Networkscited by 40
  7. 2022Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformercited by 21
  8. 2020Deepzzle: Solving Visual Jigsaw Puzzles with Deep Learning andShortest Path Optimizationcited by 20
  9. 2025Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysiscited by 3

Built on by

Not cited yet.