SoftMoR mixes all recursion-step outputs via per-token weights so recursive Vision Transformers gain accuracy from added depth with only ~1.7M extra parameters on ImageNet-1K.
When does label smoothing help?Advances in neural in- formation processing systems, 32, 2019
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
-
Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers
SoftMoR mixes all recursion-step outputs via per-token weights so recursive Vision Transformers gain accuracy from added depth with only ~1.7M extra parameters on ImageNet-1K.