AIM uses multi-stage feature guidance for self-supervised masking to improve both interpretability (EPG) and accuracy on vision benchmarks.
Top-down influence in early visual processing: a Bayesian perspective
1 Pith paper cite this work, alongside 47 external citations. Polarity classification is still indexing.
1
Pith paper citing it
47
external citations · OpenAlex
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AIM: Amending Inherent Interpretability via Self-Supervised Masking
AIM uses multi-stage feature guidance for self-supervised masking to improve both interpretability (EPG) and accuracy on vision benchmarks.