# Joint Class-Affinity Loss Correction for Robust Medical Image Segmentation with Noisy Labels

arXiv: https://arxiv.org/abs/2206.07994 · HTML: https://mlsanity.com/paper/2206.07994/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 24 references that are in the map.
- First posted on arXiv 16 Jun 2022.

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

- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Deep learning with noisy labels: exploring techniques and remedies in medical image analysis](https://mlsanity.com/paper/1912.02911/) (2019)
- [2017 Robotic Instrument Segmentation Challenge](https://mlsanity.com/paper/1902.06426/) (2019)
- [2018 Robotic Scene Segmentation Challenge](https://mlsanity.com/paper/2001.11190/) (2020)
- [Provably End-to-end Label-Noise Learning without Anchor Points](https://mlsanity.com/paper/2102.02400/) (2021)
- [Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2107.11787/) (2021)
- [ISINet: An Instance-Based Approach for Surgical Instrument Segmentation](https://mlsanity.com/paper/2007.05533/) (2020)
- [Disentangling Human Error from the Ground Truth in Segmentation of Medical Images](https://mlsanity.com/paper/2007.15963/) (2020)
- [Learning with Bounded Instance- and Label-dependent Label Noise](https://mlsanity.com/paper/1709.03768/) (2017)
- [Convolution-Free Medical Image Segmentation using Transformers](https://mlsanity.com/paper/2102.13645/) (2021)
- [MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2103.05254/) (2021)
- [Learning with Noisy Labels via Sparse Regularization](https://mlsanity.com/paper/2108.00192/) (2021)
- [RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments](https://mlsanity.com/paper/1909.10360/) (2019)
- [Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels](https://mlsanity.com/paper/2006.07831/) (2020)
- [Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentation](https://mlsanity.com/paper/2107.10100/) (2021)
- [SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2203.15202/) (2022)
- [Attention-Guided Lightweight Network for Real-Time Segmentation of Robotic Surgical Instruments](https://mlsanity.com/paper/1910.11109/) (2019)
- [Noisy Labels are Treasure: Mean-Teacher-Assisted Confident Learning for Hepatic Vessel Segmentation](https://mlsanity.com/paper/2106.01860/) (2021)
- [Effective semantic segmentation in Cataract Surgery: What matters most?](https://mlsanity.com/paper/2108.06119/) (2021)
- [Meta Corrupted Pixels Mining for Medical Image Segmentation](https://mlsanity.com/paper/2007.03538/) (2020)

## Built on by (most cited first, 8 of 8)

- [ShaSTA: Modeling Shape and Spatio-Temporal Affinities for 3D Multi-Object Tracking](https://mlsanity.com/paper/2211.03919/) (2022)
- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [Imbalanced Medical Image Segmentation with Pixel-dependent Noisy Labels](https://mlsanity.com/paper/2501.06678/) (2025)
- [Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation](https://mlsanity.com/paper/2307.05898/) (2023)
- [Clean Label Disentangling for Medical Image Segmentation with Noisy Labels](https://mlsanity.com/paper/2311.16580/) (2023)
- [Bridge the Gap Between Visual and Linguistic Comprehension for Generalized Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2503.23806/) (2025)
- [DFEN: Dual Feature Equalization Network for Medical Image Segmentation](https://mlsanity.com/paper/2505.05913/) (2025)
- [Staged Voxel-Level Deep Reinforcement Learning for 3D Medical Image Segmentation with Noisy Annotations](https://mlsanity.com/paper/2601.03875/) (2026)

## Abstract (arXiv)

Noisy labels collected with limited annotation cost prevent medical image segmentation algorithms from learning precise semantic correlations. Previous segmentation arts of learning with noisy labels merely perform a pixel-wise manner to preserve semantics, such as pixel-wise label correction, but neglect the pair-wise manner. In fact, we observe that the pair-wise manner capturing affinity relations between pixels can greatly reduce the label noise rate. Motivated by this observation, we present a novel perspective for noisy mitigation by incorporating both pixel-wise and pair-wise manners, where supervisions are derived from noisy class and affinity labels, respectively. Unifying the pixel-wise and pair-wise manners, we propose a robust Joint Class-Affinity Segmentation (JCAS) framework to combat label noise issues in medical image segmentation. Considering the affinity in pair-wise manner incorporates contextual dependencies, a differentiated affinity reasoning (DAR) module is devised to rectify the pixel-wise segmentation prediction by reasoning about intra-class and inter-class affinity relations. To further enhance the noise resistance, a class-affinity loss correction (CALC) strategy is designed to correct supervision signals via the modeled noise label distributions in class and affinity labels. Meanwhile, CALC strategy interacts the pixel-wise and pair-wise manners through the theoretically derived consistency regularization. Extensive experiments under both synthetic and real-world noisy labels corroborate the efficacy of the proposed JCAS framework with a minimum gap towards the upper bound performance. The source code is available at urlhttps://github.com/CityU-AIM-Group/JCAS.