Stratify or Die: Rethinking Data Splits in Image Segmentation

• URL: http://arxiv.org/abs/2509.21056v1
• Date: Thu, 25 Sep 2025 12:04:26 GMT
• Title: Stratify or Die: Rethinking Data Splits in Image Segmentation
• Authors: Naga Venkata Sai Jitin Jami, Thomas Altstidl, Jonas Mueller, Jindong Li, Dario Zanca, Bjoern Eskofier, Heike Leutheuser,
• Abstract summary: Iterative Pixel Stratification (IPS) is a label-aware sampling method tailored for segmentation tasks.<n>We present Wasserstein-Driven Evolutionary Stratification (WDES), a novel genetic algorithm designed to minimize the Wasserstein distance.
• Score: 6.391423612294428
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Random splitting of datasets in image segmentation often leads to unrepresentative test sets, resulting in biased evaluations and poor model generalization. While stratified sampling has proven effective for addressing label distribution imbalance in classification tasks, extending these ideas to segmentation remains challenging due to the multi-label structure and class imbalance typically present in such data. Building on existing stratification concepts, we introduce Iterative Pixel Stratification (IPS), a straightforward, label-aware sampling method tailored for segmentation tasks. Additionally, we present Wasserstein-Driven Evolutionary Stratification (WDES), a novel genetic algorithm designed to minimize the Wasserstein distance, thereby optimizing the similarity of label distributions across dataset splits. We prove that WDES is globally optimal given enough generations. Using newly proposed statistical heterogeneity metrics, we evaluate both methods against random sampling and find that WDES consistently produces more representative splits. Applying WDES across diverse segmentation tasks, including street scenes, medical imaging, and satellite imagery, leads to lower performance variance and improved model evaluation. Our results also highlight the particular value of WDES in handling small, imbalanced, and low-diversity datasets, where conventional splitting strategies are most prone to bias.

Related papers

• PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learning [17.302186298424836]
  Cross-modal retrieval aims to align different modalities via semantic similarity.<n>Existing methods often assume that image-text pairs are perfectly aligned, overlooking Noisy Correspondences in real data.
  arXiv  Detail & Related papers  (2025-09-19T05:41:17Z)
• Improving Distribution Alignment with Diversity-based Sampling [0.0]
  Domain shifts are ubiquitous in machine learning, and can substantially degrade a model's performance when deployed to real-world data. This paper proposes to improve these estimates by inducing diversity in each sampled minibatch. It simultaneously balances the data and reduces the variance of the gradients, thereby enhancing the model's generalisation ability.
  arXiv  Detail & Related papers  (2024-10-05T17:26:03Z)
• Tackling Diverse Minorities in Imbalanced Classification [80.78227787608714]
  Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers. We propose generating synthetic samples iteratively by mixing data samples from both minority and majority classes. We demonstrate the effectiveness of our proposed framework through extensive experiments conducted on seven publicly available benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-28T18:48:34Z)
• All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation [67.30502812804271]
  Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. We propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions.
  arXiv  Detail & Related papers  (2023-05-25T08:19:31Z)
• Stochastic Segmentation with Conditional Categorical Diffusion Models [3.8168879948759953]
  We propose a conditional categorical diffusion model (CCDM) for semantic segmentation based on Denoising Diffusion Probabilistic Models. Our results show that CCDM achieves state-of-the-art performance on LIDC, and outperforms established baselines on the classical segmentation dataset Cityscapes.
  arXiv  Detail & Related papers  (2023-03-15T19:16:47Z)
• Compound Batch Normalization for Long-tailed Image Classification [77.42829178064807]
  We propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. The proposed method outperforms existing methods on long-tailed image classification.
  arXiv  Detail & Related papers  (2022-12-02T07:31:39Z)
• Learning from Partially Overlapping Labels: Image Segmentation under Annotation Shift [68.6874404805223]
  We propose several strategies for learning from partially overlapping labels in the context of abdominal organ segmentation. We find that combining a semi-supervised approach with an adaptive cross entropy loss can successfully exploit heterogeneously annotated data.
  arXiv  Detail & Related papers  (2021-07-13T09:22:24Z)
• Minimax Active Learning [61.729667575374606]
  Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either rely on model uncertainty to select the most uncertain samples or use clustering or reconstruction to choose the most diverse set of unlabeled examples. We develop a semi-supervised minimax entropy-based active learning algorithm that leverages both uncertainty and diversity in an adversarial manner.
  arXiv  Detail & Related papers  (2020-12-18T19:03:40Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)

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.