Visual Explanations via Iterated Integrated Attributions
We introduce Iterated Integrated Attributions (IIA) - a generic method for explaining the predictions of vision models. IIA employs iterative integration across the input image, the internal representations generated by the model, and their gradients, yielding precise and focused explanation maps. We demonstrate the effectiveness of IIA through comprehensive evaluations across various tasks, datasets, and network architectures. Our results showcase that IIA produces accurate explanation maps, outperforming other state-of-the-art explanation techniques.
Code (1)
Similar Papers 제목 키워드 기반
A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values
Local explanation methods, also known as attribution methods, attribute a deep network's prediction to its input (cf. Baehrens et al. (2010)). We respond to the claim from Adebayo et al. (2018) that local explanation met…
AttributeSensitivityTime Series Model Attribution Visualizations as Explanations
Attributions are a common local explanation technique for deep learning models on single samples as they are easily extractable and demonstrate the relevance of input values. In many cases, heatmaps visualize such attrib…
modelPositionTime SeriesTime Series AnalysisRobust Models Are More Interpretable Because Attributions Look Normal
Recent work has found that adversarially-robust deep networks used for image classification are more interpretable: their feature attributions tend to be sharper, and are more concentrated on the objects associated with …
image-classificationImage ClassificationInterpretability Analysis of Domain Adapted Dense Retrievers
Dense retrievers have demonstrated significant potential for neural information retrieval; however, they exhibit a lack of robustness to domain shifts, thereby limiting their efficacy in zero-shot settings across diverse…
Biomedical Information RetrievalDomain AdaptationInformation RetrievalQuestion Answering+2The Manifold Hypothesis for Gradient-Based Explanations
When do gradient-based explanation algorithms provide perceptually-aligned explanations? We propose a criterion: the feature attributions need to be aligned with the tangent space of the data manifold. To provide evidenc…
Diabetic Retinopathy Detection