Matching Networks: Attention-Weighted Few-Shot Classification

Few-shot classifiers like Matching Networks never fine-tune on a new class — instead they attend over a small labelled support set and vote. This simulation lays that attention mechanism out as real 3D geometry: support points from N classes sit in an embedding plane, a draggable query point casts a distance-weighted attention line to every one of them, and the predicted class is whichever label collects the most attention mass. A sharpness slider morphs the vote continuously between a soft, blurry consensus and a hard nearest-neighbour lookup, while live readouts track prediction confidence and attention entropy as you move the query across the plane.