InfoCons uses a variational information bottleneck with an attention mask to identify which points in a point cloud most influence a model's prediction.
Learning to explain: An information-theoretic perspective on model interpretation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
InfoCons uses a variational information bottleneck with an attention mask to identify which points in a point cloud most influence a model's prediction.