Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classification

• URL: http://arxiv.org/abs/2506.01368v1
• Date: Mon, 02 Jun 2025 06:51:28 GMT
• Title: Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classification
• Authors: GaYeon Koh, Hyun-Jic Oh, Jeonghyun Noh, Won-Ki Jeong,
• Abstract summary: We propose a two-stage synthetic data augmentation framework for long-tailed food classification.<n>We generate a reference set conditioned by a positive prompt on the generation target and then select a class that shares similar features with the generation target as a negative prompt.<n>We demonstrate the efficacy of the proposed method on two long-tailed food benchmark datasets, achieving superior performance compared to previous works in terms of top-1 accuracy.
• Score: 3.3659467814492654
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning-based food image classification enables precise identification of food categories, further facilitating accurate nutritional analysis. However, real-world food images often show a skewed distribution, with some food types being more prevalent than others. This class imbalance can be problematic, causing models to favor the majority (head) classes with overall performance degradation for the less common (tail) classes. Recently, synthetic data augmentation using diffusion-based generative models has emerged as a promising solution to address this issue. By generating high-quality synthetic images, these models can help uniformize the data distribution, potentially improving classification performance. However, existing approaches face challenges: fine-tuning-based methods need a uniformly distributed dataset, while pre-trained model-based approaches often overlook inter-class separation in synthetic data. In this paper, we propose a two-stage synthetic data augmentation framework, leveraging pre-trained diffusion models for long-tailed food classification. We generate a reference set conditioned by a positive prompt on the generation target and then select a class that shares similar features with the generation target as a negative prompt. Subsequently, we generate a synthetic augmentation set using positive and negative prompt conditions by a combined sampling strategy that promotes intra-class diversity and inter-class separation. We demonstrate the efficacy of the proposed method on two long-tailed food benchmark datasets, achieving superior performance compared to previous works in terms of top-1 accuracy.

Related papers

• Leveraging Diffusion Models for Synthetic Data Augmentation in Protein Subcellular Localization Classification [0.0]
  We implement a class-conditional denoising diffusion probabilistic model (DDPM) to produce label-consistent samples.<n>We explore their integration with real data via two hybrid training strategies: Mix Loss and Mix Representation.<n>Our findings highlight the importance of realistic data generation and robust supervision when incorporating generative augmentation into biomedical image classification.
  arXiv  Detail & Related papers  (2025-05-28T22:58:50Z)
• Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Class [20.606333546028516]
  We show that state-of-the-art deep generative models yield significantly lower-quality minority examples than majority examples.<n>We propose a novel technique of converting the binary class labels to ternary class labels by introducing a class for the region where minority and majority distributions overlap.
  arXiv  Detail & Related papers  (2024-12-20T08:15:20Z)
• Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences [20.629333587044012]
  We study the impact of data curation on iterated retraining of generative models. We prove that, if the data is curated according to a reward model, the expected reward of the iterative retraining procedure is maximized.
  arXiv  Detail & Related papers  (2024-06-12T21:28:28Z)
• Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
  We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-04-26T06:00:27Z)
• Training Class-Imbalanced Diffusion Model Via Overlap Optimization [55.96820607533968]
  Diffusion models trained on real-world datasets often yield inferior fidelity for tail classes. Deep generative models, including diffusion models, are biased towards classes with abundant training images. We propose a method based on contrastive learning to minimize the overlap between distributions of synthetic images for different classes.
  arXiv  Detail & Related papers  (2024-02-16T16:47:21Z)
• Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling [69.60713300418467]
  Learning to jump is a general recipe for generative modeling of various types of data. We demonstrate when learning to jump is expected to perform comparably to learning to denoise, and when it is expected to perform better.
  arXiv  Detail & Related papers  (2023-05-28T05:38:28Z)
• Class-Balancing Diffusion Models [57.38599989220613]
  Class-Balancing Diffusion Models (CBDM) are trained with a distribution adjustment regularizer as a solution. Our method benchmarked the generation results on CIFAR100/CIFAR100LT dataset and shows outstanding performance on the downstream recognition task.
  arXiv  Detail & Related papers  (2023-04-30T20:00:14Z)
• Your Diffusion Model is Secretly a Zero-Shot Classifier [90.40799216880342]
  We show that density estimates from large-scale text-to-image diffusion models can be leveraged to perform zero-shot classification. Our generative approach to classification attains strong results on a variety of benchmarks. Our results are a step toward using generative over discriminative models for downstream tasks.
  arXiv  Detail & Related papers  (2023-03-28T17:59:56Z)
• Diffusing Gaussian Mixtures for Generating Categorical Data [21.43283907118157]
  We propose a generative model for categorical data based on diffusion models with a focus on high-quality sample generation. Our method of evaluation highlights the capabilities and limitations of different generative models for generating categorical data.
  arXiv  Detail & Related papers  (2023-03-08T14:55:32Z)
• A Relational Model for One-Shot Classification [80.77724423309184]
  We show that a deep learning model with built-in inductive bias can bring benefits to sample-efficient learning, without relying on extensive data augmentation. The proposed one-shot classification model performs relational matching of a pair of inputs in the form of local and pairwise attention.
  arXiv  Detail & Related papers  (2021-11-08T07:53:12Z)

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.