Context Embedding Networks

09/22/2017
by   Kun ho Kim, et al.
0

Low dimensional embeddings that capture the main variations of interest in collections of data are important for many applications. One way to construct these embeddings is to acquire estimates of similarity from the crowd. However, similarity is a multi-dimensional concept that varies from individual to individual. Existing models for learning embeddings from the crowd typically make simplifying assumptions such as all individuals estimate similarity using the same criteria, the list of criteria is known in advance, or that the crowd workers are not influenced by the data that they see. To overcome these limitations we introduce Context Embedding Networks (CENs). In addition to learning interpretable embeddings from images, CENs also model worker biases for different attributes along with the visual context i.e. the visual attributes highlighted by a set of images. Experiments on two noisy crowd annotated datasets show that modeling both worker bias and visual context results in more interpretable embeddings compared to existing approaches.

READ FULL TEXT

page 3

page 5

page 7

page 8

page 10

research
04/04/2020

Measuring Social Biases of Crowd Workers using Counterfactual Queries

Social biases based on gender, race, etc. have been shown to pollute mac...
research
08/16/2019

Zero-Shot Crowd Behavior Recognition

Understanding crowd behavior in video is challenging for computer vision...
research
04/29/2016

An expressive dissimilarity measure for relational clustering using neighbourhood trees

Clustering is an underspecified task: there are no universal criteria fo...
research
08/04/2020

Wisdom of crowds: much ado about nothing

The puzzling idea that the combination of independent estimates of the m...
research
04/10/2019

Context-Aware Embeddings for Automatic Art Analysis

Automatic art analysis aims to classify and retrieve artistic representa...
research
09/16/2020

Human biases in body measurement estimation

Body measurements, including weight and height, are key indicators of he...
research
10/18/2021

Topologically Regularized Data Embeddings

Unsupervised feature learning often finds low-dimensional embeddings tha...

Please sign up or login with your details

Forgot password? Click here to reset