Semantic Bottleneck Networks add interpretable semantic concept layers to deep networks, recovering SOTA segmentation performance with drastic channel reduction and enabling failure interpretation at over 99% accuracy for most outputs.
The (Un)reliability of saliency methods
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. We use a simple and common pre-processing step ---adding a constant shift to the input data--- to show that a transformation with no effect on the model can cause numerous methods to incorrectly attribute. In order to guarantee reliability, we posit that methods should fulfill input invariance, the requirement that a saliency method mirror the sensitivity of the model with respect to transformations of the input. We show, through several examples, that saliency methods that do not satisfy input invariance result in misleading attribution.
representative citing papers
citing papers explorer
-
Interpretability Beyond Classification Output: Semantic Bottleneck Networks
Semantic Bottleneck Networks add interpretable semantic concept layers to deep networks, recovering SOTA segmentation performance with drastic channel reduction and enabling failure interpretation at over 99% accuracy for most outputs.
- The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics