Injecting EDM-style noise into masked-token position embeddings and adding two auxiliary losses improves I-JEPA's linear-probing accuracy by about 1.5 points on ImageNet-1K.
Stochastic positional embeddings improve masked image modeling, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Improving Joint Embedding Predictive Architecture with Diffusion Noise
Injecting EDM-style noise into masked-token position embeddings and adding two auxiliary losses improves I-JEPA's linear-probing accuracy by about 1.5 points on ImageNet-1K.