Pith. sign in

Label-efficient se- mantic segmentation with diffusion models, 2022

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Understanding Trade offs When Conditioning Synthetic Data

cs.CV · 2025-07-03 · conditional · novelty 6.0

Diverse layout-plus-prompt conditioning of diffusion models generates synthetic data that improves few-shot object detection mAP by up to 177% over real-data-only training, while prompt-only conditioning wins when conditions are scarce.

citing papers explorer

Showing 1 of 1 citing paper.

  • Understanding Trade offs When Conditioning Synthetic Data cs.CV · 2025-07-03 · conditional · none · ref 3

    Diverse layout-plus-prompt conditioning of diffusion models generates synthetic data that improves few-shot object detection mAP by up to 177% over real-data-only training, while prompt-only conditioning wins when conditions are scarce.