RelDrop, which occludes the most attribution-relevant input regions during training, improves generalization and occlusion robustness for image and point cloud classification.
How to explain individual classification decisions.Journal of Machine Learning Research, 11: 1803–1831, 2010
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Relevance-driven Input Dropout: an Explanation-guided Regularization Technique
RelDrop, which occludes the most attribution-relevant input regions during training, improves generalization and occlusion robustness for image and point cloud classification.