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

arXiv: https://arxiv.org/abs/2108.11900 · HTML: https://mlsanity.com/paper/2108.11900/

## 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 (most cited first, 30 of 32)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images](https://mlsanity.com/paper/1808.08114/) (2018)
- [Generative Adversarial Network in Medical Imaging: A Review](https://mlsanity.com/paper/1809.07294/) (2018)
- [Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis](https://mlsanity.com/paper/1908.06912/) (2019)
- [On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location](https://mlsanity.com/paper/2003.07064/) (2020)
- [Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation](https://mlsanity.com/paper/2007.09886/) (2020)
- [Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains](https://mlsanity.com/paper/2007.02035/) (2020)
- [An Overview of Deep Semi-Supervised Learning](https://mlsanity.com/paper/2006.05278/) (2020)
- [Normalized Cut Loss for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1804.01346/) (2018)
- [Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation](https://mlsanity.com/paper/1904.06346/) (2019)
- [Multi-scale self-guided attention for medical image segmentation](https://mlsanity.com/paper/1906.02849/) (2019)
- [Learn To Pay Attention](https://mlsanity.com/paper/1804.02391/) (2018)
- [Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction](https://mlsanity.com/paper/1907.02757/) (2019)
- [Constrained-CNN losses for weakly supervised segmentation](https://mlsanity.com/paper/1805.04628/) (2018)
- [Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology Images](https://mlsanity.com/paper/2007.05448/) (2020)
- [Learning to Segment Medical Images with Scribble-Supervision Alone](https://mlsanity.com/paper/1807.04668/) (2018)
- [Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision](https://mlsanity.com/paper/2004.06816/) (2020)
- [PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation](https://mlsanity.com/paper/2011.12640/) (2020)
- [Scribble-based Domain Adaptation via Co-segmentation](https://mlsanity.com/paper/2007.03632/) (2020)
- [Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty](https://mlsanity.com/paper/2011.07221/) (2020)
- [Weakly supervised segmentation with cross-modality equivariant constraints](https://mlsanity.com/paper/2104.02488/) (2021)
- [Incorporating prior knowledge in medical image segmentation: a survey](https://mlsanity.com/paper/1607.01092/) (2016)

## Built on by (most cited first, 4 of 4)

- [Transferable Time-Series Forecasting under Causal Conditional Shift](https://mlsanity.com/paper/2111.03422/) (2021)
- [Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets](https://mlsanity.com/paper/2408.12489/) (2024)
- [Text-Driven Weakly Supervised OCT Lesion Segmentation with Structural Guidance](https://mlsanity.com/paper/2411.12615/) (2024)
- [Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2603.06374/) (2026)

## 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.