Pith. sign in

(8) Classification head

· d · L , F LOP sAIM = O ( 3X s=0 18 · rexp · d · W H 4s + (2 · rexp + r2 exp) · d2 · W H 4s ) · L 4 ! = O ( 765 128 · rexp + 85 128 · (rexp + r2 exp) · d) · d · W H· L · 2024

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Deep Tree Tensor Networks

cs.CV · 2025-02-14 · conditional · novelty 4.0

DTTN is a multilinear, activation-free architecture built from antisymmetric interaction modules that reaches 82.4% top-1 accuracy on ImageNet-1k and is claimed to unfold into a tree tensor network.

citing papers explorer

Showing 1 of 1 citing paper.

  • Deep Tree Tensor Networks cs.CV · 2025-02-14 · conditional · none · ref 1

    DTTN is a multilinear, activation-free architecture built from antisymmetric interaction modules that reaches 82.4% top-1 accuracy on ImageNet-1k and is claimed to unfold into a tree tensor network.