Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
arXiv preprint arXiv:1911.04944 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
DunbaaBERT releases competitive Urdu encoder models trained from scratch, with the 32k-vocab variant showing the best efficiency profile across acceptability, classification, and sentiment tasks.
citing papers explorer
-
Vision Transformers Need Registers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
-
DunbaaBERT: From Sacrifice to Semantics
DunbaaBERT releases competitive Urdu encoder models trained from scratch, with the 32k-vocab variant showing the best efficiency profile across acceptability, classification, and sentiment tasks.