HyperAdapter performs PEFT of ViTs via soft hypergraph construction, hyperedge-level bottleneck adaptation, and incidence-based diffusion, claiming consistent gains over token-wise adapters on structured visual benchmarks.
arXiv preprint arXiv:2210.00788 (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers
HyperAdapter performs PEFT of ViTs via soft hypergraph construction, hyperedge-level bottleneck adaptation, and incidence-based diffusion, claiming consistent gains over token-wise adapters on structured visual benchmarks.