2 papers
cs.CV2026
Consistent text-to-image generation via scene de-contextualization
Song Tang, Peihao Gong, Kunyu Li +5
Consistent text-to-image (T2I) generation seeks to produce identity-preserving images of the same subject across diverse scenes, yet it often fails due to a phenomenon called ident…
cs.CV2025
Source-Free Domain Adaptive Object Detection with Semantics Compensation
Song Tang, Jiuzheng Yang, Mao Ye +3
Strong data augmentation is a fundamental component of state-of-the-art mean teacher-based Source-Free domain adaptive Object Detection (SFOD) methods, enabling consistency-based s…