Salient Imagenet

Class: 168 (Redbone Coonhound), Feature: 2033

This feature is core for class Redbone Coonhound. It is the second most important feature for class Redbone Coonhound.

Below, we display the five Redbone Coonhound 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	The main object is redbone dog whose some part got focus.
Main Object	3	Focus is on head which is a part of redbone
Main Object	4	Focus is on some part of the main object
Main Object	5	Most of the images are mainly focused on main object's body parts like eyes, mouth.
Main Object	5	Focus is on the face of the dog

core

Class: 168 (Redbone Coonhound), Feature: 2033

MTurk Worker Annotations

Related Class-Feature Pairs

Important Features for Redbone Coonhound

Classes where Feature 2033 is among Most Important (i.e. top-5)