DOE OSTI · code-158797
SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification
Abstract
SInkhorn Dynamic Domain Adaptation (SIDDA) supplements the experiments presented in 2501.14048, SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification with Equivariant Neural Networks. SIDDA introduces a semi-supervised, automatic domain adaptation method that leverages Sinkhorn divergences to dynamically adjust the regularization in the optimal transport plan and the weighting between classification and domain adaptation loss terms during training.
Keep this discovery
Explore connections, maps & timelines
Pandya, Sneh [Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Northeastern Univ., Boston, MA (United States)] (0009000725369022), Patel, Purvik [Argonne National Laboratory (ANL), Argonne, IL (United States); Northeastern Univ., Boston, MA (United States)] (0009000223142987), Nord, Brian [Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Univ. of Chicago, IL (United States)] (0000000167068972), Walmsley, Mike [Univ. of Manchester (United Kingdom); Univ. of Toronto, ON (Canada)] (0000000264084181), Ćiprijanović, Aleksandra [Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Univ. of Chicago, IL (United States)] (0000000312817192). 2025-07-25. SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification. https://doi.org/10.11578/dc.20250725.11
Cite the original work for its findings. Save a collection to share your selection of sources.