MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images

• URL: http://arxiv.org/abs/2505.18741v1
• Date: Sat, 24 May 2025 15:20:47 GMT
• Title: MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images
• Authors: Han Li, Hu Han, S. Kevin Zhou,
• Abstract summary: How to leverage training images with diverse qualities becomes a problem in learning deep models.<n>We propose a novel Mixed-order Minibatch Sampling (MoMBS) method to optimize the use of training samples with diverse qualities.
• Score: 38.1134869118573
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Natural images exhibit label diversity (clean vs. noisy) in noisy-labeled image classification and prevalence diversity (abundant vs. sparse) in long-tailed image classification. Similarly, medical images in universal lesion detection (ULD) exhibit substantial variations in image quality, encompassing attributes such as clarity and label correctness. How to effectively leverage training images with diverse qualities becomes a problem in learning deep models. Conventional training mechanisms, such as self-paced curriculum learning (SCL) and online hard example mining (OHEM), relieve this problem by reweighting images with high loss values. Despite their success, these methods still confront two challenges: (i) the loss-based measure of sample hardness is imprecise, preventing optimum handling of different cases, and (ii) there exists under-utilization in SCL or over-utilization OHEM with the identified hard samples. To address these issues, this paper revisits the minibatch sampling (MBS), a technique widely used in deep network training but largely unexplored concerning the handling of diverse-quality training samples. We discover that the samples within a minibatch influence each other during training; thus, we propose a novel Mixed-order Minibatch Sampling (MoMBS) method to optimize the use of training samples with diverse qualities. MoMBS introduces a measure that takes both loss and uncertainty into account to surpass a sole reliance on loss and allows for a more refined categorization of high-loss samples by distinguishing them as either poorly labeled and under represented or well represented and overfitted. We prioritize under represented samples as the main gradient contributors in a minibatch and keep them from the negative influences of poorly labeled or overfitted samples with a mixed-order minibatch sampling design.

Related papers

• Detection of Under-represented Samples Using Dynamic Batch Training for Brain Tumor Segmentation from MR Images [0.8437187555622164]
  Brain tumors in magnetic resonance imaging (MR) are difficult, time-consuming, and prone to human error. These challenges can be resolved by developing automatic brain tumor segmentation methods from MR images. Various deep-learning models based on the U-Net have been proposed for the task. These deep-learning models are trained on a dataset of tumor images and then used for segmenting the masks.
  arXiv  Detail & Related papers  (2024-08-21T21:51:47Z)
• Deep Boosting Multi-Modal Ensemble Face Recognition with Sample-Level Weighting [11.39204323420108]
  Deep convolutional neural networks have achieved remarkable success in face recognition. The current training benchmarks exhibit an imbalanced quality distribution. This poses issues for generalization on hard samples since they are underrepresented during training. Inspired by the well-known AdaBoost, we propose a sample-level weighting approach to incorporate the importance of different samples into the FR loss.
  arXiv  Detail & Related papers  (2023-08-18T01:44:54Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix [30.532481130511137]
  Deep-learning-based image classification frameworks often suffer from the noisy label problem caused by the inter-observer variation. We propose a plugin module, namely noise ignoring block (NIB), to separate the hard samples from the mislabeled ones. Our NIB module consistently improves the performances of the state-of-the-art robust training methods.
  arXiv  Detail & Related papers  (2021-10-17T17:01:57Z)
• A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection [93.38607559281601]
  We devise a hierarchical generative model that captures the multi-scale patch distribution of each training image. The anomaly score is obtained by aggregating the patch-based votes of the correct transformation across scales and image regions.
  arXiv  Detail & Related papers  (2021-04-29T17:49:48Z)
• ReMix: Towards Image-to-Image Translation with Limited Data [154.71724970593036]
  We propose a data augmentation method (ReMix) to tackle this issue. We interpolate training samples at the feature level and propose a novel content loss based on the perceptual relations among samples. The proposed approach effectively reduces the ambiguity of generation and renders content-preserving results.
  arXiv  Detail & Related papers  (2021-03-31T06:24:10Z)
• Jo-SRC: A Contrastive Approach for Combating Noisy Labels [58.867237220886885]
  We propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency) Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its "likelihood" of being clean or out-of-distribution.
  arXiv  Detail & Related papers  (2021-03-24T07:26:07Z)
• Salvage Reusable Samples from Noisy Data for Robust Learning [70.48919625304]
  We propose a reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images. Our key idea is to additionally identify and correct reusable samples, and then leverage them together with clean examples to update the networks.
  arXiv  Detail & Related papers  (2020-08-06T02:07:21Z)
• Melanoma Detection using Adversarial Training and Deep Transfer Learning [6.22964000148682]
  We propose a two-stage framework for automatic classification of skin lesion images. In the first stage, we leverage the inter-class variation of the data distribution for the task of conditional image synthesis. In the second stage, we train a deep convolutional neural network for skin lesion classification.
  arXiv  Detail & Related papers  (2020-04-14T22:46:20Z)

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.