Image retrieval outperforms diffusion models on data augmentation
Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large datasets, often with noisy annotations, and it remains an open question to which extent these models contrib...
Main Authors: | Burg, MF, Wenzel, F, Zietlow, D, Horn, M, Makansi, O, Locatello, F, Russell, C |
---|---|
Format: | Journal article |
Language: | English |
Published: |
Journal of Machine Learning Research
2023
|
Similar Items
-
Retrieval-augmented human motion generation with diffusion model
by: Guo, Xinying
Published: (2023) -
Plant trait retrieval from hyperspectral data: Collective efforts in scientific data curation outperform simulated data derived from the PROSAIL model
by: Daniel Mederer, et al.
Published: (2025-01-01) -
Paired cross-modal data augmentation for fine-grained image-to-text retrieval
by: Wang, Hao, et al.
Published: (2023) -
In-Context Retrieval-Augmented Language Models
by: Ori Ram, et al.
Published: (2023-11-01) -
Art, Artfulness, or Artifice?: A Review of The Art of Statistics: How to Learn From Data, by David Spiegelhalter
by: Jason Makansi
Published: (2020-01-01)