The choice of head_idx

[kwea123]

dino-vit-features/extractor.py

Line 313 in 79c1289

head_idxs = [0, 2, 4, 5]

Is there any reason why you choose these heads?

[ShirAmir]

We found that heads 1 and 3 attend to background information in ViT-S, so we decided to disregard them for saliency map creation. The method still works comparably well when using all heads, at the cost of adjusting some parameters.