Proto-FG3D replaces the softmax classifier with prototype matching for fine-grained 3D shape classification, reporting state-of-the-art accuracy on FG3D and ModelNet40 with built-in interpretability.
3d2seqviews: Aggregating sequential views for 3d global feature learning by cnn with hierarchical attention aggregation.IEEE Transactions on Image Processing, 28(8):3986–3999, 2019
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.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification
Proto-FG3D replaces the softmax classifier with prototype matching for fine-grained 3D shape classification, reporting state-of-the-art accuracy on FG3D and ModelNet40 with built-in interpretability.