A two-stage diffusion-based data augmentation pipeline with confusing-class negative prompts improves long-tailed food image classification accuracy on Food101-LT and VFN-LT.
A systematic study of the class imbalance problem in convolu- tional neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classification
A two-stage diffusion-based data augmentation pipeline with confusing-class negative prompts improves long-tailed food image classification accuracy on Food101-LT and VFN-LT.