Salient Imagenet

Class: 265 (Toy Poodle), Feature: 1745

This feature is core for class Toy Poodle. It is the second most important feature for class Toy Poodle.

Below, we display the five Toy Poodle 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	3	Focus is on the animal
Main Object	4	Focus is on the face of the poodle.
Main Object	3	Red highlight is on the dog.
Main Object	4	The red region in the highlighted visual attributes focuses on the face of a toy poodle dog.
Main Object	5	The red region completely focuses on the predicted object but doesn't cover it fully.

core

Related Class-Feature Pairs

Important Features for Toy Poodle

There are 5 features annotated as core and 0 features annotated as spurious for Toy Poodle. Core features include 203, 218, 1059, 1745, 1985.

Classes where Feature 1745 is among Most Important (i.e. top-5)

Feature 1745 is core for the following classes: Irish Wolfhound, Otterhound, Scottish Deerhound, Border Terrier, Irish Terrier, Norfolk Terrier, Lakeland Terrier, Airedale Terrier, Cairn Terrier, Soft-Coated Wheaten Terrier, Toy Poodle.