Beyond Pairwise Repulsion: Collective Diversity via Determinant Maximization in Diffusion Sampling
Diffusion models often collapse samples onto high-density modes, limiting diversity for tasks like data augmentation. DetNO proposes maximizing diversity by treating a batch as a whole, using the log-determinant of an RBF Gram matrix over noise predictions. This collective volume maximization outperforms pairwise repulsion methods and yields statistically significant accuracy gains in few-shot classification.