The paper proposes a robust B-spline decoupling framework using constrained coupled matrix-tensor factorization and the R-CMTF-BSD algorithm for compressing Vision and Swin Transformer models.
Strategies for applying low rank decomposition to transformer- based models, in: 36th Conference on Neural Information Processing Sys- tems (NeurIPS2022), pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust Basis Spline Decoupling for the Compression of Transformer Models
The paper proposes a robust B-spline decoupling framework using constrained coupled matrix-tensor factorization and the R-CMTF-BSD algorithm for compressing Vision and Swin Transformer models.