3 papers
cs.LG2026
Task-Directed Residual AddUNet:Perfect-Reconstruction Routing for Full-Rate Representations
Vikram R. Lakkavalli
This paper establishes a perfect-reconstruction (PR) interpretation of AddUNet and its full-rate realization, and introduces a Residual Full-Rate PR architecture for task-directed…
cs.CV2026
Multi-Task Learning with Additive U-Net for Image Denoising and Classification
Vikram Lakkavalli, Neelam Sinha
We investigate additive skip fusion in U-Net architectures for image denoising and denoising-centric multi-task learning (MTL). By replacing concatenative skips with gated additive…
cs.CV2026
Rethinking Skip Connections: Additive U-Net for Robust and Interpretable Denoising
Vikram R Lakkavalli
Skip connections are central to U-Net architectures for image denoising, but standard concatenation doubles channel dimensionality and obscures information flow, allowing uncontrol…