Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, William, Wu, Xindi, Deng, Zhiwei, Tureci, Esin, Russakovsky, Olga
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913174548119552
author Yang, William
Wu, Xindi
Deng, Zhiwei
Tureci, Esin
Russakovsky, Olga
author_facet Yang, William
Wu, Xindi
Deng, Zhiwei
Tureci, Esin
Russakovsky, Olga
contents Text-to-image (T2I) models are increasingly used for synthetic dataset generation, but generating effective synthetic training data for classification remains challenging. Fine-tuning a T2I model with a few real examples can help improve the quality of synthetic training data; however, it may also cause overfitting and reduce diversity in the generated samples. We propose a fine-tuning strategy BOB (BeyondOBjects) to mitigate these concerns for fine-grained classification. Given a small set of real examples, we first extract class-agnostic attributes such as scene background and object pose. We then explicitly condition on these attributes during fine-tuning of the T2I model and marginalize them out during generation. This design mitigates overfitting, preserves the T2I model's generative prior, reduces estimation errors, and further minimizes unintended inter-class associations. Extensive experiments across multiple T2I models, backbones, and datasets show that our method achieves state-of-the-art performance in low-shot fine-grained classification when augmented with synthetic data. Concretely, BOB outperforms DataDream by 7.4% on the Aircraft dataset (from 50.0% to 57.4% when fine-tuning a CLIP classifier with five real images augmented with 100 synthetic images). In three of the four benchmarks, fine-tuning downstream models with 5 real images augmented with BOB achieves better performance than fine-tuning with 10 real images. Collectively, BOB outperforms prior art in 18 of 24 experimental settings, with 2+% accuracy improvements in 14 of these settings.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24078
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification
Yang, William
Wu, Xindi
Deng, Zhiwei
Tureci, Esin
Russakovsky, Olga
Computer Vision and Pattern Recognition
Text-to-image (T2I) models are increasingly used for synthetic dataset generation, but generating effective synthetic training data for classification remains challenging. Fine-tuning a T2I model with a few real examples can help improve the quality of synthetic training data; however, it may also cause overfitting and reduce diversity in the generated samples. We propose a fine-tuning strategy BOB (BeyondOBjects) to mitigate these concerns for fine-grained classification. Given a small set of real examples, we first extract class-agnostic attributes such as scene background and object pose. We then explicitly condition on these attributes during fine-tuning of the T2I model and marginalize them out during generation. This design mitigates overfitting, preserves the T2I model's generative prior, reduces estimation errors, and further minimizes unintended inter-class associations. Extensive experiments across multiple T2I models, backbones, and datasets show that our method achieves state-of-the-art performance in low-shot fine-grained classification when augmented with synthetic data. Concretely, BOB outperforms DataDream by 7.4% on the Aircraft dataset (from 50.0% to 57.4% when fine-tuning a CLIP classifier with five real images augmented with 100 synthetic images). In three of the four benchmarks, fine-tuning downstream models with 5 real images augmented with BOB achieves better performance than fine-tuning with 10 real images. Collectively, BOB outperforms prior art in 18 of 24 experimental settings, with 2+% accuracy improvements in 14 of these settings.
title Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.24078