Salient Imagenet

Class: 167 (English Foxhound), Feature: 2003

This feature is core for class English Foxhound. It is the second most important feature for class English Foxhound.

Below, we display the five English Foxhound images that most highly activate the feature, along with the Neural Activation Map (heatmap) and Feature Attack for each image. These are the same as the images shown to crowdworkers to annotate this class-feature pair.

We additionally provide the full responses of the five crowdworkers that annotated this pair, as well as links to other related pairs (i.e. same class or same feature).

MTurk Worker Annotations

core

spurious

core

spurious

Main Focus	Confidence	Explanation
Main Object	4	Focus is on the limbs of the foxhound.
Main Object	4	Focus is on the dogs
Main Object	4	Most of the images is focusing on some part of the main objects
Main Object	4	Based on images 1-5.
Main Object	4	Torso of the dog is highlighted. right underneath the dogs head, chest area.

core

Class: 167 (English Foxhound), Feature: 2003

MTurk Worker Annotations

Related Class-Feature Pairs

Important Features for English Foxhound

Classes where Feature 2003 is among Most Important (i.e. top-5)