PEPR reframes learning with privileged event data as predicting latent event features from RGB to improve domain generalization in object detection and segmentation without direct cross-modal alignment.
Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers
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
-
PEPR: Privileged Event-based Predictive Regularization for Domain Generalization
PEPR reframes learning with privileged event data as predicting latent event features from RGB to improve domain generalization in object detection and segmentation without direct cross-modal alignment.