i-WiViG is an interpretable window vision GNN that constrains nodes to disjoint local windows and applies learnable sparse attention to identify relevant subgraphs, delivering competitive performance on scene classification and regression with natural and remote-sensing images.
Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
i-WiViG: Interpretable Window Vision GNN
i-WiViG is an interpretable window vision GNN that constrains nodes to disjoint local windows and applies learnable sparse attention to identify relevant subgraphs, delivering competitive performance on scene classification and regression with natural and remote-sensing images.