Towards Ground Truth Evaluation of Visual Explanations
Citations
75 citations
51 citations
Cites background from "Towards Ground Truth Evaluation of ..."
...Efforts to quantify the utility of attribution methods or apply sanity checks have been undertaken in input domains where human intuition is usually used to evaluate attribution quality [4, 50, 7, 32, 21, 5], like images and text....
[...]
48 citations
34 citations
Cites background from "Towards Ground Truth Evaluation of ..."
...It is worth noting that such interpretability aspects are also attracting wide interest in computer vision (Bach et al., 2015; Bau et al., 2017; Bhatt et al., 2020; Dabkowski and Gal, 2017; Escalante et al., 2018; Fong et al., 2019; Fong and Vedaldi, 2017; Goh et al., 2020; Osman et al., 2020; Murdoch et al., 2019; Petsiuk et al., 2020; 2018; Ribeiro et al., 2016; Samek et al., 2020; 2017; Zhang et al., 2020; Belharbi et al., 2021) and medical imaging (de La Torre et al....
[...]
25 citations
Cites methods from "Towards Ground Truth Evaluation of ..."
...Note we omit evaluation criteria that assume access to ground-truth explanations for training points; for a thorough treatment on this topic, see [Hind et al., 2019; Osman et al., 2020]....
[...]
References
30,811 citations
24,672 citations
12,783 citations
"Towards Ground Truth Evaluation of ..." refers methods in this paper
...Methods that provide such heatmaps in a direct and unambiguous way include, amongst others, Class Saliency Map [21], Occlusion [24], Gradient × Input, Integrated Gradients [23], Layer-wise Relevance Propagation [6], Excitation Backpropagation [26], Guided Backpropagation [22]....
[...]
11,104 citations
8,424 citations