Cut-and-Paste Dataset Generation for Balancing Domain Gaps in Object Instance Detection

no code implementations • 26 Sep 2019 • Woo-han Yun, Taewoo Kim, Jaeyeon Lee, Jaehong Kim, Junmo Kim

Then, we show that the original cut-and-paste approach suffers from a new domain gap problem, an unbalanced domain gaps, because it has two separate source domains for foreground and background, unlike the conventional domain shift problem.

Domain Adaptation Generative Adversarial Network +2