Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator

• URL: http://arxiv.org/abs/2604.07122v1
• Date: Wed, 08 Apr 2026 14:18:00 GMT
• Title: Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator
• Abstract summary: A conventional semi-supervised learning method, ClassMix, pastes class labels predicted from unlabeled images onto other images.<n>We propose a method where class labels from labeled images, along with the corresponding image regions, are pasted onto unlabeled images and their pseudo-labeled images.<n>We introduce a method that trains the model to make predictions on unlabeled images more similar to those on labeled images.
• Score: 17.179617344873275
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to enhance the performance, has gained attention. A conventional semi-supervised learning method, ClassMix, pastes class labels predicted from unlabeled images onto other images. However, since ClassMix performs operations using pseudo-labels obtained from unlabeled images, there is a risk of handling inaccurate labels. Additionally, there is a gap in data quality between labeled and unlabeled images, which can impact the feature maps. This study addresses these two issues. First, we propose a method where class labels from labeled images, along with the corresponding image regions, are pasted onto unlabeled images and their pseudo-labeled images. Second, we introduce a method that trains the model to make predictions on unlabeled images more similar to those on labeled images. Experiments on the Chase and COVID-19 datasets demonstrated an average improvement of 2.07% in mIoU compared to conventional semi-supervised learning methods.

Related papers

• Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning [4.5810803542748495]
  We introduce Positive and Unlabeled Learning (PU learning), which uses only positive and unlabeled data for binary classification problems.<n>Our PU learning makes us easy to select pseudo-labels for various background regions.
  arXiv  Detail & Related papers  (2025-08-11T02:11:49Z)
• Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation [15.815414883505722]
  In semi-supervised medical image segmentation, there exist empirical mismatch problems between labeled and unlabeled data distribution. We propose a straightforward method for alleviating the problem - copy-pasting labeled and unlabeled data bidirectionally. We show that the experiments show solid gains (e.g., over 21% Dice improvement on ACDC dataset with 5% labeled data) compared with other state-of-the-arts on various semi-supervised medical image segmentation datasets.
  arXiv  Detail & Related papers  (2023-05-01T06:06:51Z)
• Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing Labels [30.79809627981242]
  We introduce a label correction mechanism to identify missing labels, then define a unique contrastive loss for multi-label image classification with missing labels (CLML) Different from existing multi-label CL losses, CLML also preserves low-rank global and local label dependencies in the latent representation space. The proposed strategy has been shown to improve the classification performance of the Resnet101 model by margins of 1.2%, 1.6%, and 1.3% respectively on three standard datasets.
  arXiv  Detail & Related papers  (2022-09-03T02:44:07Z)
• Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels [86.17081952197788]
  We propose to blend category-specific representation across different images to transfer information of known labels to complement unknown labels. Experiments on the MS-COCO, Visual Genome, Pascal VOC 2007 datasets show that the proposed SARB framework obtains superior performance over current leading competitors.
  arXiv  Detail & Related papers  (2022-03-04T07:56:16Z)
• GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference [90.5402652758316]
  We propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net. It uses labeled information to guide the learning of unlabeled instances. It achieves competitive segmentation accuracy and significantly improves the mIoU by +7$%$ compared to previous approaches.
  arXiv  Detail & Related papers  (2021-12-28T06:48:03Z)
• Mixed Supervision Learning for Whole Slide Image Classification [88.31842052998319]
  We propose a mixed supervision learning framework for super high-resolution images. During the patch training stage, this framework can make use of coarse image-level labels to refine self-supervised learning. A comprehensive strategy is proposed to suppress pixel-level false positives and false negatives.
  arXiv  Detail & Related papers  (2021-07-02T09:46:06Z)
• GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference [153.354332374204]
  We propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net. We first introduce a feature alignment objective between labeled and unlabeled data to capture potentially similar image pairs. MITrans is shown to be a powerful knowledge module for further progressive refining features of unlabeled data. Along with supervised learning for labeled data, the prediction of unlabeled data is jointly learned with the generated pseudo masks.
  arXiv  Detail & Related papers  (2021-06-29T02:48:45Z)
• Multi-Label Learning from Single Positive Labels [37.17676289125165]
  Predicting all applicable labels for a given image is known as multi-label classification. We show that it is possible to approach the performance of fully labeled classifiers despite training with significantly fewer confirmed labels.
  arXiv  Detail & Related papers  (2021-06-17T17:58:04Z)
• KRADA: Known-region-aware Domain Alignment for Open World Semantic Segmentation [64.03817806316903]
  In semantic segmentation, we aim to train a pixel-level classifier to assign category labels to all pixels in an image. In an open world, the unlabeled test images probably contain unknown categories and have different distributions from the labeled images. We propose an end-to-end learning framework, known-region-aware domain alignment (KRADA), to distinguish unknown classes while aligning distributions of known classes in labeled and unlabeled open-world images.
  arXiv  Detail & Related papers  (2021-06-11T08:43:59Z)
• Grafit: Learning fine-grained image representations with coarse labels [114.17782143848315]
  This paper tackles the problem of learning a finer representation than the one provided by training labels. By jointly leveraging the coarse labels and the underlying fine-grained latent space, it significantly improves the accuracy of category-level retrieval methods.
  arXiv  Detail & Related papers  (2020-11-25T19:06:26Z)

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.