mlsanityData to 14 Oct 2026

Self-supervised Multi-scale Consistency for Weakly Supervised Segmentation Learning

arXiv 2108.11900 ↗First posted 26 Aug 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Collecting large-scale medical datasets with fine-grained annotations is time-consuming and requires experts. For this reason, weakly supervised learning aims at optimising machine learning models using weaker forms of annotations, such as scribbles, which are easier and faster to collect. Unfortunately, training with weak labels is challenging and needs regularisation. Herein, we introduce a novel self-supervised multi-scale consistency loss, which, coupled with an attention mechanism, encourages the segmentor to learn multi-scale relationships between objects and improves performance. We show state-of-the-art performance on several medical and non-medical datasets. The code used for the experiments is available at https://vios-s.github.io/multiscale-pyag.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 32 of its 39 references that are in the map. First posted on arXiv 26 Aug 2021.

Builds on

32 of 39 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  5. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  6. 2018Self-Attention Generative Adversarial Networkscited by 809
  7. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  8. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 331
  9. 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
  10. 2018Attention Gated Networks: Learning to Leverage Salient Regions in Medical Imagescited by 272
  11. 2018Generative Adversarial Network in Medical Imaging: A Reviewcited by 257
  12. 2019Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysiscited by 159
20 more
  1. 2020On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Locationcited by 142
  2. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  3. 2020Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domainscited by 124
  4. 2020An Overview of Deep Semi-Supervised Learningcited by 121
  5. 2018Normalized Cut Loss for Weakly-supervised CNN Segmentationcited by 112
  6. 2019Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentationcited by 88
  7. 2019Multi-scale self-guided attention for medical image segmentationcited by 84
  8. 2018Learn To Pay Attentioncited by 83
  9. 2019Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Predictioncited by 70
  10. 2018Constrained-CNN losses for weakly supervised segmentationcited by 62
  11. 2020Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology Imagescited by 55
  12. 2018Learning to Segment Medical Images with Scribble-Supervision Alonecited by 48
  13. 2020Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervisioncited by 40
  14. 2020PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentationcited by 36
  15. 2020Scribble-based Domain Adaptation via Co-segmentationcited by 34
  16. 2020Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertaintycited by 26
  17. 2021Weakly supervised segmentation with cross-modality equivariant constraintscited by 18
  18. 2016Incorporating prior knowledge in medical image segmentation: a surveycited by 13
  19. 2020ACCL: Adversarial constrained-CNN loss for weakly supervised medical image segmentationcited by 13
  20. 2019Temporal Consistency Objectives Regularize the Learning of Disentangled Representationscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 2; 2025: 0; 2026: 1.

4 papers.

  1. 2021Transferable Time-Series Forecasting under Causal Conditional Shiftcited by 18
  2. 2024Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasetscited by 4
  3. 2024Text-Driven Weakly Supervised OCT Lesion Segmentation with Structural Guidancecited by 0
  4. 2026Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentationcited by 0