VMINet, a backbone built entirely from Mamba-inspired separable self-attention blocks with a position-encoding triangular mask, matches or beats Vision Mamba on classification and dense prediction benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Separable Self-attention Inspired by the State Space Model for Computer Vision
VMINet, a backbone built entirely from Mamba-inspired separable self-attention blocks with a position-encoding triangular mask, matches or beats Vision Mamba on classification and dense prediction benchmarks.