NAVE clusters multi-depth feature activations of frozen CNNs and vision transformers into interpretable segmentation maps for post-hoc model inspection.
PloS ONE10(7), e0130140 (2015) 1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Depth Concept Extraction for Post-Hoc Vision Encoder Explanation
NAVE clusters multi-depth feature activations of frozen CNNs and vision transformers into interpretable segmentation maps for post-hoc model inspection.