AtteConDA adds attention-based conflict suppression to multi-condition diffusion models so that generated driving-scene images retain richer structural cues from the original annotations.
Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, and Quoc V
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
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
AtteConDA: Attention-Based Conflict Suppression in Multi-Condition Diffusion Models and Synthetic Data Augmentation
AtteConDA adds attention-based conflict suppression to multi-condition diffusion models so that generated driving-scene images retain richer structural cues from the original annotations.