The paper quantifies and visualizes the layer-wise evolution of Vision GNN graphs, showing a shift from local, visually similar connections to long-range, class-specific connections that do not align with human perception.
In: 2020 33rd SIBGRAPI Con- ference on Graphics, Patterns and Images (SIBGRAPI)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explaining Vision GNNs: A Semantic and Visual Analysis of Graph-based Image Classification
The paper quantifies and visualizes the layer-wise evolution of Vision GNN graphs, showing a shift from local, visually similar connections to long-range, class-specific connections that do not align with human perception.