Saliency-guided superimposition augmentation, where a policy's FullGrad saliency sets per-pixel blending weights, improves behavior cloning robustness to visual domain shifts while preserving in-domain performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Visual Domain Robustness in Behaviour Cloning via Saliency-Guided Augmentation
Saliency-guided superimposition augmentation, where a policy's FullGrad saliency sets per-pixel blending weights, improves behavior cloning robustness to visual domain shifts while preserving in-domain performance.