Pointing game

anchor

Evaluation protocol, not an explanation method. Checks whether the highest-scoring region of an explanation falls inside the annotated object. Measures localisation, not faithfulness, and the score is binary per image, so it cannot tell a narrow hit from a diffuse one. Introduced by Zhang et al. alongside Excitation Backprop.

Findings

• FX-001Pairwise Banzhaf interactions explain CLIP similarity more faithfully than single-score methods [eval]
• FX-002FIXLIP gives SigLIP-2 higher pointing-game recognition than CLIP at ViT-B/32 and ViT-B/16 [eval]
• IC-447CLIP ViT-B/16 produces noisy saliency maps and contains only 42 concept detectors, indicating poor visual interpretability [eval]
• IC-450LLaVA with the original CLIP encoder produces noisy, non-sparse attention maps that poorly localize to the objects described in generated text [eval]