Salient Imagenet

Class: 168 (Redbone Coonhound), Feature: 1911

This feature is core for class Redbone Coonhound. It is the 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	1	The focus appears to be on the dogs but the amplified images do not represent this well
Main Object	5	All the images are mainly focused on main object's body parts.
Main Object	5	The focus is on the dog's neck and head.
Main Object	4	Focus is on some part of the main object

core

Related Class-Feature Pairs

Important Features for Redbone Coonhound

There are 5 features annotated as core and 0 features annotated as spurious for Redbone Coonhound. Core features include 66, 747, 976, 1911, 2033.

Classes where Feature 1911 is among Most Important (i.e. top-5)

Feature 1911 is core for the following classes: King Charles Spaniel, Rhodesian Ridgeback, Redbone Coonhound, Irish Terrier, Vizsla, Irish Setter, Welsh Springer Spaniel, Sussex Spaniel, Dhole, Common Sorrel Horse, Orangutan, Proboscis Monkey.