2 papers
cs.CV2025
Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
Xu Cai, Yang Wu, Qianli Chen +3
We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel veloci…
cs.CV2025
Graph Aggregation Prototype Learning for Semantic Change Detection in Remote Sensing
Zhengyi Xu, Haoran Wu, Wen Jiang +1
Semantic change detection (SCD) extends the binary change detection task to provide not only the change locations but also the detailed "from-to" categories in multi-temporal remot…