Channel importance splits into task relevance and local replaceability; local-axis metrics predict safe removal under pruning better than target-axis metrics across multiple CNNs and datasets.
Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf
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
-
Task Relevance Is Not Local Replaceability: A Two-Axis View of Channel Information
Channel importance splits into task relevance and local replaceability; local-axis metrics predict safe removal under pruning better than target-axis metrics across multiple CNNs and datasets.