439 citations · 446 across the 5 of their papers we have counts for
5 papers
OrthoDiffusion: A Generalizable Multi-Task Diffusion Foundation Model for Musculoskeletal MRI Interpretation
Tian Lan, Lei Xu, Zimu Yuan +8
Musculoskeletal disorders represent a significant global health burden and are a leading cause of disability worldwide. While MRI is essential for accurate diagnosis, its interpret…
Conditioning Residuals for Diffusion Models via Representation Feedback
Weilai Xiang, Hongyu Yang, Di Huang +1
Diffusion models now serve as a common foundation for multimedia generation, and useful intermediate representations emerge during their generative training. Standard architectures…
Faster Ray Tracing through Hierarchy Cut Code
WeiLai Xiang, FengQi Liu, Dan Li +4
We propose a novel ray reordering technique to accelerate the ray tracing process by encoding and sorting rays prior to traversal. Instead of spatial coordinates, our method encode…
Denoising Diffusion Autoencoders are Unified Self-supervised Learners
Weilai Xiang, Hongyu Yang, Di Huang +1
Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classif…
AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
Xuan Zhang, Hao Luo, Xing Fan +6
In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features. Global feature learning benefits greatly fr…