BASIC: Semi-supervised Multi-organ Segmentation with Balanced Subclass Regularization and Semantic-conflict Penalty
- URL: http://arxiv.org/abs/2501.03580v1
- Date: Tue, 07 Jan 2025 07:08:46 GMT
- Title: BASIC: Semi-supervised Multi-organ Segmentation with Balanced Subclass Regularization and Semantic-conflict Penalty
- Authors: Zhenghao Feng, Lu Wen, Yuanyuan Xu, Binyu Yan, Xi Wu, Jiliu Zhou, Yan Wang,
- Abstract summary: We propose an innovative semi-supervised network with BAlanced Subclass regularIzation and semantic-Conflict penalty mechanism (BASIC) to learn the unbiased knowledge for semi-supervised multi-organ segmentation (MoS)
Considering the similar semantic information inside the subclasses and their corresponding original classes, we devise a semantic-conflict penalty mechanism to give heavier punishments to the conflicting SCS predictions with wrong parent classes.
- Score: 10.492173873748214
- License:
- Abstract: Semi-supervised learning (SSL) has shown notable potential in relieving the heavy demand of dense prediction tasks on large-scale well-annotated datasets, especially for the challenging multi-organ segmentation (MoS). However, the prevailing class-imbalance problem in MoS caused by the substantial variations in organ size exacerbates the learning difficulty of the SSL network. To address this issue, in this paper, we propose an innovative semi-supervised network with BAlanced Subclass regularIzation and semantic-Conflict penalty mechanism (BASIC) to effectively learn the unbiased knowledge for semi-supervised MoS. Concretely, we construct a novel auxiliary subclass segmentation (SCS) task based on priorly generated balanced subclasses, thus deeply excavating the unbiased information for the main MoS task with the fashion of multi-task learning. Additionally, based on a mean teacher framework, we elaborately design a balanced subclass regularization to utilize the teacher predictions of SCS task to supervise the student predictions of MoS task, thus effectively transferring unbiased knowledge to the MoS subnetwork and alleviating the influence of the class-imbalance problem. Considering the similar semantic information inside the subclasses and their corresponding original classes (i.e., parent classes), we devise a semantic-conflict penalty mechanism to give heavier punishments to the conflicting SCS predictions with wrong parent classes and provide a more accurate constraint to the MoS predictions. Extensive experiments conducted on two publicly available datasets, i.e., the WORD dataset and the MICCAI FLARE 2022 dataset, have verified the superior performance of our proposed BASIC compared to other state-of-the-art methods.
Related papers
- On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning [19.898602404329697]
Exemplar-free class incremental learning (EF-CIL) is a nontrivial task that requires continuously enriching model capability with new classes while maintaining previously learned knowledge without storing and replaying any old class exemplars.
An emerging theory-guided framework for CIL trains task-specific models for a shared network, shifting the pressure of forgetting to task-id prediction.
In EF-CIL, task-id prediction is more challenging due to the lack of inter-task interaction (e.g., replays of exemplars)
arXiv Detail & Related papers (2025-01-26T08:50:33Z) - Alleviating Class Imbalance in Semi-supervised Multi-organ Segmentation via Balanced Subclass Regularization [3.5622306331369993]
We present a two-phase semi-supervised network (BSR-Net) with balanced subclass regularization for multi-organ segmentation (MoS)
In Phase I, we introduce a class-balanced subclass generation strategy based on balanced clustering.
In Phase II, we design an auxiliary subclass segmentation task within the multi-task framework of the main MoS task.
The SCS task contributes a balanced subclass regularization to the main MoS task and transfers unbiased knowledge to the MoS network.
arXiv Detail & Related papers (2024-08-26T07:02:17Z) - Sequential Binary Classification for Intrusion Detection [0.0]
IDS datasets suffer from high class imbalance, which impacts the performance of standard ML models.
This paper explores a structural approach to handling class imbalance in multi-class classification problems.
Experiments on benchmark IDS datasets demonstrate that the structural approach to handling class-imbalance, as exemplified by SBC, is a viable approach to handling the issue.
arXiv Detail & Related papers (2024-06-10T08:34:13Z) - Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection [111.0991686509715]
We study the class imbalance problem for semi-supervised object detection (SSOD) under more challenging scenarios.
We propose a simple yet effective gradient-based sampling framework that tackles the class imbalance problem from the perspective of two types of confirmation biases.
Experiments on three proposed sub-tasks, namely MS-COCO, MS-COCO to Object365 and LVIS, suggest that our method outperforms current class imbalanced object detectors by clear margins.
arXiv Detail & Related papers (2024-03-22T11:30:10Z) - Uncertainty-guided Boundary Learning for Imbalanced Social Event
Detection [64.4350027428928]
We propose a novel uncertainty-guided class imbalance learning framework for imbalanced social event detection tasks.
Our model significantly improves social event representation and classification tasks in almost all classes, especially those uncertain ones.
arXiv Detail & Related papers (2023-10-30T03:32:04Z) - Cross-head mutual Mean-Teaching for semi-supervised medical image
segmentation [6.738522094694818]
Semi-supervised medical image segmentation (SSMIS) has witnessed substantial advancements by leveraging limited labeled data and abundant unlabeled data.
Existing state-of-the-art (SOTA) methods encounter challenges in accurately predicting labels for the unlabeled data.
We propose a novel Cross-head mutual mean-teaching Network (CMMT-Net) incorporated strong-weak data augmentation.
arXiv Detail & Related papers (2023-10-08T09:13:04Z) - Meta-Causal Feature Learning for Out-of-Distribution Generalization [71.38239243414091]
This paper presents a balanced meta-causal learner (BMCL), which includes a balanced task generation module (BTG) and a meta-causal feature learning module (MCFL)
BMCL effectively identifies the class-invariant visual regions for classification and may serve as a general framework to improve the performance of the state-of-the-art methods.
arXiv Detail & Related papers (2022-08-22T09:07:02Z) - CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep
Learning [55.733193075728096]
Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance.
Sample re-weighting methods are popularly used to alleviate this data bias issue.
We propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data.
arXiv Detail & Related papers (2022-02-11T13:49:51Z) - Boosting Discriminative Visual Representation Learning with
Scenario-Agnostic Mixup [54.09898347820941]
We propose textbfScenario-textbfAgnostic textbfMixup (SAMix) for both Self-supervised Learning (SSL) and supervised learning (SL) scenarios.
Specifically, we hypothesize and verify the objective function of mixup generation as optimizing local smoothness between two mixed classes.
A label-free generation sub-network is designed, which effectively provides non-trivial mixup samples and improves transferable abilities.
arXiv Detail & Related papers (2021-11-30T14:49:59Z) - Analyzing Overfitting under Class Imbalance in Neural Networks for Image
Segmentation [19.259574003403998]
In image segmentation neural networks may overfit to the foreground samples from small structures.
In this study, we provide new insights on the problem of overfitting under class imbalance by inspecting the network behavior.
arXiv Detail & Related papers (2021-02-20T14:57:58Z) - Revisiting LSTM Networks for Semi-Supervised Text Classification via
Mixed Objective Function [106.69643619725652]
We develop a training strategy that allows even a simple BiLSTM model, when trained with cross-entropy loss, to achieve competitive results.
We report state-of-the-art results for text classification task on several benchmark datasets.
arXiv Detail & Related papers (2020-09-08T21:55:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.