Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasets

• URL: http://arxiv.org/abs/2608.18907v1
• Date: Wed, 19 Aug 2026 13:31:21 GMT
• Title: Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasets
• Abstract summary: Small-scale image classification is often limited by the scarcity of training data.<n>We propose learning-state-aware dynamic generative data augmentation (LSADA)
• Score: 17.158132143614356
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Small-scale image classification is often limited by the scarcity of training data. Generative data augmentation (GDA) based on pretrained generative models has emerged as an effective solution. However, existing methods rely on task-agnostic augmentation strategies that overlook downstream model needs. Although recent dynamic GDA methods incorporate model feedback to guide augmentation, they still struggle to reliably determine sample-specific augmentation strengths and adapt augmentation strategies to different image regions while balancing image diversity and class semantics. To address these issues, we propose learning-state-aware dynamic generative data augmentation (LSADA). Specifically, LSADA constructs a learning state for each sample based on its current loss and loss-decrease rate, which is then mapped to a sample-specific augmentation strength. Furthermore, LSADA introduces a decoupled data augmentation and diffusion fusion strategy that applies strength-controlled transformations to class-relevant regions and generates diverse class-irrelevant regions, progressively fusing them to improve image diversity while preserving class semantics. Experiments on nine public datasets show that LSADA outperforms the existing SOTA dynamic GDA method by an average of 4.5% on six natural image datasets and 2.5% on three medical image datasets.

Related papers

• Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled Data [1.0901840476380924]
  This paper introduces a novel dual-region augmentation approach designed to reduce reliance on large-scale labeled datasets.<n>Our method performs targeted data transformations by applying random noise perturbations to foreground objects.<n>By augmenting training data through structured transformations, our method enables model generalization across domains.
  arXiv  Detail & Related papers  (2025-04-17T16:42:33Z)
• Diffusion-Enhanced Test-time Adaptation with Text and Image Augmentation [67.37146712877794]
  IT3A is a novel test-time adaptation method that utilizes a pre-trained generative model for multi-modal augmentation of each test sample from unknown new domains.<n>By combining augmented data from pre-trained vision and language models, we enhance the ability of the model to adapt to unknown new test data.<n>In a zero-shot setting, IT3A outperforms state-of-the-art test-time prompt tuning methods with a 5.50% increase in accuracy.
  arXiv  Detail & Related papers  (2024-12-12T20:01:24Z)
• SGIA: Enhancing Fine-Grained Visual Classification with Sequence Generative Image Augmentation [16.642582574494742]
  We introduce Sequence Generative Image Augmentation (SGIA) for augmenting Fine-Grained Visual Classification (FGVC) datasets.<n>Our method features a unique Bridging Transfer Learning process, designed to minimize the domain gap between real and synthetically augmented data.<n>Our work sets a new benchmark and outperforms the previous state-of-the-art models in classification accuracy by 0.5% for the CUB-200-2011 dataset.
  arXiv  Detail & Related papers  (2024-12-09T01:39:46Z)
• Data Augmentation for Image Classification using Generative AI [8.74488498507946]
  Data augmentation is a promising solution to expanding the dataset size. Recent approaches use generative AI models to improve dataset diversity. We propose the Automated Generative Data Augmentation (AGA)
  arXiv  Detail & Related papers  (2024-08-31T21:16:43Z)
• 3D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable Editing [52.68314936128752]
  We propose a new paradigm to automatically generate 3D labeled training data by harnessing the power of pretrained large foundation models. For each target semantic class, we first generate 2D images of a single object in various structure and appearance via diffusion models and chatGPT generated text prompts. We transform these augmented images into 3D objects and construct virtual scenes by random composition.
  arXiv  Detail & Related papers  (2024-08-25T09:31:22Z)
• A Simple Background Augmentation Method for Object Detection with Diffusion Model [53.32935683257045]
  In computer vision, it is well-known that a lack of data diversity will impair model performance. We propose a simple yet effective data augmentation approach by leveraging advancements in generative models. Background augmentation, in particular, significantly improves the models' robustness and generalization capabilities.
  arXiv  Detail & Related papers  (2024-08-01T07:40:00Z)
• Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation [8.777277201807351]
  We present SaSPA: Structure and Subject Preserving Augmentation.<n>Our method does not use real images as guidance, thereby increasing generation flexibility and promoting greater diversity.<n>We conduct extensive experiments and benchmark SaSPA against both traditional and recent generative data augmentation methods.
  arXiv  Detail & Related papers  (2024-06-20T17:58:30Z)
• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• Additional Look into GAN-based Augmentation for Deep Learning COVID-19 Image Classification [57.1795052451257]
  We study the dependence of the GAN-based augmentation performance on dataset size with a focus on small samples. We train StyleGAN2-ADA with both sets and then, after validating the quality of generated images, we use trained GANs as one of the augmentations approaches in multi-class classification problems. The GAN-based augmentation approach is found to be comparable with classical augmentation in the case of medium and large datasets but underperforms in the case of smaller datasets.
  arXiv  Detail & Related papers  (2024-01-26T08:28:13Z)
• Training on Thin Air: Improve Image Classification with Generated Data [28.96941414724037]
  Diffusion Inversion is a simple yet effective method to generate diverse, high-quality training data for image classification. Our approach captures the original data distribution and ensures data coverage by inverting images to the latent space of Stable Diffusion. We identify three key components that allow our generated images to successfully supplant the original dataset.
  arXiv  Detail & Related papers  (2023-05-24T16:33:02Z)
• Effective Data Augmentation With Diffusion Models [45.18188726287581]
  We address the lack of diversity in data augmentation with image-to-image transformations parameterized by pre-trained text-to-image diffusion models.<n>Our method edits images to change their semantics using an off-the-shelf diffusion model, and generalizes to novel visual concepts from a few labelled examples.<n>We evaluate our approach on few-shot image classification tasks, and on a real-world weed recognition task, and observe an improvement in accuracy in tested domains.
  arXiv  Detail & Related papers  (2023-02-07T20:42:28Z)
• Local Magnification for Data and Feature Augmentation [53.04028225837681]
  We propose an easy-to-implement and model-free data augmentation method called Local Magnification (LOMA) LOMA generates additional training data by randomly magnifying a local area of the image. Experiments show that our proposed LOMA, though straightforward, can be combined with standard data augmentation to significantly improve the performance on image classification and object detection.
  arXiv  Detail & Related papers  (2022-11-15T02:51:59Z)

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.