[KongchangAI]
Concept遮挡法

Occlusion

A perturbation-based post-hoc explanation method that measures importance by systematically occluding different parts of the input and observing changes in model output. It is model-agnostic but computationally expensive.

Timeline (last 90 days)

Oct 28

The evaluation results show that only a few methods maintain consistent performance across all evaluation criteria, among which Occlusion performs best overall on the two dimensions of faithfulness and interpretability.

Unverified50%
Oct 28

Occlusion is a class of perturbation-based post-hoc explanation methods that measures importance by systematically occluding different parts of the input and observing changes in the model's output probabilities.

Unverified50%
Oct 28

Occlusion's advantages are being model-agnostic and conceptually intuitive; its disadvantages are that computational cost grows with the number of occlusion units and that it is sensitive to the choice of occlusion granularity.

Unverified50%

All Facts (3)

Source Articles