Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification
In this paper, we address a key scientific problem in machine learning: Given a training set for an image classification task, can we train a generative model on this dataset to enhance the classification performance? (i.e., closed-set generative data augmentation). We start by exploring the distinctions and similarities between real images and closed-set synthetic images generated by advanced generative models. Through extensive experiments, we offer systematic insights into the effective use of closed-set synthetic data for augmentation. Notably, we empirically determine the equivalent scale of synthetic images needed for augmentation. In addition, we also show quantitative equivalence between the real data augmentation and open-set generative augmentation (generative models trained using data beyond the given training set). While it aligns with the common intuition that real images are generally preferred, our empirical formulation also offers a guideline to quantify the increased scale of synthetic data augmentation required to achieve comparable image classification performance. Our results on natural and medical image datasets further illustrate how this effect varies with the baseline training set size and the amount of synthetic data incorporated.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ClassificationData AugmentationSimilar Papers 제목 키워드 기반
The Gaussian equivalence of generative models for learning with shallow neural networks
Understanding the impact of data structure on the computational tractability of learning is a key challenge for the theory of neural networks. Many theoretical works do not explicitly model training data, or assume that …
BIG-bench Machine LearningExploring Large Language Models for Ontology Alignment
This work investigates the applicability of recent generative Large Language Models (LLMs), such as the GPT series and Flan-T5, to ontology alignment for identifying concept equivalence mappings across ontologies. To tes…
Delta-Closure Structure for Studying Data Distribution
In this paper, we revisit pattern mining and study the distribution underlying a binary dataset thanks to the closure structure which is based on passkeys, i.e., minimum generators in equivalence classes robust to noise.…
Can the Rookies Cut the Tough Cookie? Exploring the Use of LLMs for SQL Equivalence Checking
Equivalence checking of SQL queries is an intractable problem often encountered in settings ranging from grading SQL submissions to debugging query optimizers. Despite recent work toward developing practical solutions, o…
In-Context LearningOn Equivalence and Cores for Incomplete Databases in Open and Closed Worlds
Data exchange heavily relies on the notion of incomplete database instances. Several semantics for such instances have been proposed and include open (OWA), closed (CWA), and open-closed (OCWA) world. For all these seman…