Figure 2

A snapshot of the experiment. See “Methods” section and Table 1 for the naming conventions of the conditions used below. The experimental condition above the black line is [specific labels] & [helpful] & [blur]. Under the black line is the [jet] equivalent of the second row, which is obtained by replacing the blurring maps with the jet color maps. Experimental conditions with generic labels are obtained by replacing specific labels—‘Flagpole” and “Barn” in this case—with generic category names—“Category A” and “Category B.” Experimental conditions without the saliency maps, i.e., [no map], show only the first row of images. Conditions without examples, i.e., [no examples], show only the first column of image (s). All images and saliency maps shown were 224-by-224 pixels. The prediction of the model to be explained on the target image is “Flagpole” in this case. All photographs are obtained from the open-source ImageNet 1K dataset³⁸. This figure was created using Adobe Illustrator CS6 (v. 16.0.0)⁴³.