One-Step Generative Modeling via Unbalanced Optimal Transport
Drifting models enable one-step generation by amortizing distribution transport into training, but this efficiency places greater demands on the transport field estimated at each update. In large-scale training, the field is computed from finite mini-batches of generated and real samples, which provide only imperfect a...
Yi-Rong Shen, Mengfei Xia, Jun-Peng Jing et al.
· 0 citations