U-CAM uses gradients of aleatoric and predictive uncertainty losses to sharpen visual attention maps and improve VQA accuracy over standard baselines.
Weight uncertainty in neural network
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
U-CAM: Visual Explanation using Uncertainty based Class Activation Maps
U-CAM uses gradients of aleatoric and predictive uncertainty losses to sharpen visual attention maps and improve VQA accuracy over standard baselines.