pith. sign in

Similar to the standard grapher layers in the ViG model, in the GSAT block we perform the operations in the following order to the graph node:

Further, to obtain an inherently interpretable model that reveals the relevant subgraph for its prediction, we insert the GSAT graph in the final stage before the prediction head t

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.CV 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

i-WiViG: Interpretable Window Vision GNN

cs.CV · 2025-03-11 · unverdicted · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • i-WiViG: Interpretable Window Vision GNN cs.CV · 2025-03-11 · unverdicted · none · ref 38

    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.