Salient Imagenet

Class: 234 (Rottweiler), Feature: 220

This feature is core for class Rottweiler. It is the third most important feature for class Rottweiler.

Below, we display the five Rottweiler 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	5	Focus is on cheeks of rottweiler
Main Object	5	All the images are mainly focused on main object's body parts.
Main Object	5	Focus is on face of rottweiler
Main Object	4	Focus is on the cheeks of the rottweiler.
Main Object	3	Focus is on cheek of a rottweiler

core

Related Class-Feature Pairs

Important Features for Rottweiler

There are 5 features annotated as core and 0 features annotated as spurious for Rottweiler. Core features include 220, 271, 747, 1313, 1385.

Classes where Feature 220 is among Most Important (i.e. top-5)

Feature 220 is core for the following classes: American Robin, Black And Tan Coonhound, Gordon Setter, Rottweiler, Dobermann, Miniature Pinscher, Greater Swiss Mountain Dog, Bernese Mountain Dog, Entlebucher Sennenhund.