Salient Imagenet

Class: 234 (Rottweiler), Feature: 1385

This feature is core for class Rottweiler. It is the second 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 nose of rottweiler
Main Object	5	Focus is on face of rottweiler.
Main Object	4	Focus is on eyes which is a part of rottweiler
Main Object	4	The main object is rottweiler whose some part got focus.
Main Object	5	All the images are mainly focused on main object's body parts.

core

Class: 234 (Rottweiler), Feature: 1385

MTurk Worker Annotations

Related Class-Feature Pairs

Important Features for Rottweiler

Classes where Feature 1385 is among Most Important (i.e. top-5)