4 papers
Retimed Bellman Flows: Escaping the Impossible Triangle of Velocity Bootstrapping
Boyang Xu, Shengzhe Chen, Hao Yan
Flow critics learn return distributions by transporting Gaussian noise to Bellman endpoints via continuous velocity fields. While velocity bootstrapping stabilizes training by quer…
Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
Shengzhe Chen, Mehrdad Moradi, Kamran Paynabar +1
We propose Flow Mismatching, an unsupervised anomaly detection method that deliberately avoids reconstruction-based paradigms. Instead, we treat flow matching as geometric dynamics…
D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentation
Shengzhe Chen, Hao Yan
Convexity is a fundamental geometric prior that underlies many natural and man-made structures, yet remains challenging to impose effectively in end-to-end trainable segmentation n…
Contour Flow Constraint: Preserving Global Shape Similarity for Deep Learning based Image Segmentation
Shengzhe Chen, Zhaoxuan Dong, Jun Liu
For effective image segmentation, it is crucial to employ constraints informed by prior knowledge about the characteristics of the areas to be segmented to yield favorable segmenta…