# Bi-Level Collaborative Learning for Few-Shot Scribble-Supervised Medical Image Segmentation

arXiv: https://arxiv.org/abs/2607.25432 · HTML: https://mlsanity.com/paper/2607.25432/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation](https://mlsanity.com/paper/1908.10454/) (2019)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Normalized Cut Loss for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1804.01346/) (2018)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision](https://mlsanity.com/paper/2203.01475/) (2022)
- [Scribble-Supervised Medical Image Segmentation via Dual-Branch Network and Dynamically Mixed Pseudo Labels Supervision](https://mlsanity.com/paper/2203.02106/) (2022)
- [Scribble-based Hierarchical Weakly Supervised Learning for Brain Tumor Segmentation](https://mlsanity.com/paper/1911.02014/) (2019)
- [Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentation](https://mlsanity.com/paper/2107.10100/) (2021)
- [ScribbleVC: Scribble-supervised Medical Image Segmentation with Vision-Class Embedding](https://mlsanity.com/paper/2307.16226/) (2023)
- [Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation](https://mlsanity.com/paper/2110.08589/) (2021)
- [Separated Contrastive Learning for Organ-at-Risk and Gross-Tumor-Volume Segmentation with Limited Annotation](https://mlsanity.com/paper/2112.02743/) (2021)
- [Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions](https://mlsanity.com/paper/2507.20400/) (2025)
- [ModelMix: A New Model-Mixup Strategy to Minimize Vicinal Risk across Tasks for Few-scribble based Cardiac Segmentation](https://mlsanity.com/paper/2406.13237/) (2024)
- [ScribbleVS: Scribble-Supervised Medical Image Segmentation via Dynamic Competitive Pseudo Label Selection](https://mlsanity.com/paper/2411.10237/) (2024)
- [Rethinking Boundary Detection in Deep Learning-Based Medical Image Segmentation](https://mlsanity.com/paper/2505.04652/) (2025)
- [Efficient Penalty-Based Bilevel Methods: Improved Analysis, Novel Updates, and Flatness Condition](https://mlsanity.com/paper/2511.16796/) (2025)

## Abstract (arXiv)

Scribble annotations offer an efficient alternative to costly pixel-wise labeling for medical image segmentation, yet in real clinical scenarios, scribble-annotated samples are often still limited, imposing the dual challenges of sparse supervision and annotated sample scarcity. These compounded constraints severely deprive models of the structural evidence needed for complete region recovery and precise boundary delineation. To break this bottleneck, we propose a bi-level collaborative learning framework for few-shot scribble-supervised medical image segmentation. Specifically, an upper-level learnable superpixel model is introduced to provide region-structural priors for lower-level segmentation, while superpixel-based region-wise pseudo-label propagation and a spatial-prior-guided filtering strategy are performed to generate reliable dense pseudo-labels for segmentation learning. Meanwhile, the anatomical semantics learned by the lower-level segmentation model under the guidance of the current superpixels are fed back to the upper level, further driving it to learn region-structural representations better aligned with the segmentation task. Through bidirectional interaction and collaborative learning between the upper and lower levels, the proposed framework significantly outperforms existing state-of-the-art scribble-supervised methods on the ACDC and Prostate datasets under the few-shot scribble-supervised setting.