7 papers
Unregistered Spectral Image Fusion: Unmixing, Adversarial Learning, and Recoverability
Jiahui Song, Sagar Shrestha, Xiao Fu
This paper addresses the fusion of a pair of spatially unregistered hyperspectral image (HSI) and multispectral image (MSI) covering roughly overlapping regions. HSIs offer high sp…
Domain Transfer Becomes Identifiable via a Single Alignment
Sagar Shrestha, Subash Timilsina, Hoang-Son Nguyen +1
Domain transfer (DT) maps source to target distributions and supports tasks such as unsupervised image-to-image translation, single-cell analysis, and cross-platform medical imagin…
Content-Style Identification via Differential Independence
Subash Timilsina, Hoang-Son Nguyen, Sagar Shrestha +1
Generative analysis often models multi-domain observations as nonlinear mixtures of domain-invariant content variables and domain-specific style variables. Identifying both factors…
Finetuning-Free Personalization of Text to Image Generation via Hypernetworks
Sagar Shrestha, Gopal Sharma, Luowei Zhou +1
Personalizing text-to-image diffusion models has traditionally relied on subject-specific fine-tuning approaches such as DreamBooth~\cite{ruiz2023dreambooth}, which are computation…
NP-Completeness of Multicast Beamforming in Wireless Communication
Sagar Shrestha
In this work, the classical problem of multi-cast beamforming in wireless communication is reconsidered. An existing work has shown that the multi-cast beamforming problem is NP-ha…
Communication-Efficient Distributed Asynchronous ADMM
Sagar Shrestha
In distributed optimization and federated learning, asynchronous alternating direction method of multipliers (ADMM) serves as an attractive option for large-scale optimization, dat…