# Self-paced and self-consistent co-training for semi-supervised image segmentation

arXiv: https://arxiv.org/abs/2011.00325 · HTML: https://mlsanity.com/paper/2011.00325/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2020.

## Built on by (most cited first, 18 of 18)

- [Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation](https://mlsanity.com/paper/2207.14191/) (2022)
- [HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations](https://mlsanity.com/paper/2303.06242/) (2023)
- [Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels](https://mlsanity.com/paper/2107.13741/) (2021)
- [Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation](https://mlsanity.com/paper/2108.03429/) (2021)
- [PA-Seg: Learning from Point Annotations for 3D Medical Image Segmentation using Contextual Regularization and Cross Knowledge Distillation](https://mlsanity.com/paper/2208.05669/) (2022)
- [Nuclei Segmentation with Point Annotations from Pathology Images via Self-Supervised Learning and Co-Training](https://mlsanity.com/paper/2202.08195/) (2022)
- [Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions](https://mlsanity.com/paper/2303.12484/) (2023)
- [DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2412.12492/) (2024)
- [Segmentation with mixed supervision: Confidence maximization helps knowledge distillation](https://mlsanity.com/paper/2109.10902/) (2021)
- [Leveraging Labeling Representations in Uncertainty-based Semi-supervised Segmentation](https://mlsanity.com/paper/2203.05682/) (2022)
- [EPL: Evidential Prototype Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2404.06181/) (2024)
- [Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID](https://mlsanity.com/paper/2211.03626/) (2022)
- [Inherent Consistent Learning for Accurate Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2303.14175/) (2023)
- [Semi-supervised Medical Image Segmentation via Geometry-aware Consistency Training](https://mlsanity.com/paper/2202.06104/) (2022)
- [On the pitfalls of entropy-based uncertainty for multi-class semi-supervised segmentation](https://mlsanity.com/paper/2203.03587/) (2022)
- [Adaptive Mix for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2407.21586/) (2024)
- [Fully Differentiable Bidirectional Dual-Task Synergistic Learning for Semi-Supervised 3D Medical Image Segmentation](https://mlsanity.com/paper/2602.09378/) (2026)
- [Diversified Multi-prototype Representation for Semi-supervised Segmentation](https://mlsanity.com/paper/2111.08651/) (2021)

## Abstract (arXiv)

Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent co-training method. To help distillate information from unlabeled images, we first design a self-paced learning strategy for co-training that lets jointly-trained neural networks focus on easier-to-segment regions first, and then gradually consider harder ones.This is achieved via an end-to-end differentiable loss inthe form of a generalized Jensen Shannon Divergence(JSD). Moreover, to encourage predictions from different networks to be both consistent and confident, we enhance this generalized JSD loss with an uncertainty regularizer based on entropy. The robustness of individual models is further improved using a self-ensembling loss that enforces their prediction to be consistent across different training iterations. We demonstrate the potential of our method on three challenging image segmentation problems with different image modalities, using small fraction of labeled data. Results show clear advantages in terms of performance compared to the standard co-training baselines and recently proposed state-of-the-art approaches for semi-supervised segmentation