Adding a lightweight iterative top-down feedback loop to ViTs and Transformers is claimed to improve accuracy by up to 1.3 percentage points and reduce perplexity by about 6 percent, with little added overhead.
Hinton, Peter Dayan, Brendan J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Contextual Feedback Loops: Amplifying Deep Reasoning with Iterative Top-Down Feedback
Adding a lightweight iterative top-down feedback loop to ViTs and Transformers is claimed to improve accuracy by up to 1.3 percentage points and reduce perplexity by about 6 percent, with little added overhead.