Jointly Learning Multiple Measures of Similarities from Triplet Comparisons

03/05/2015
by   Liwen Zhang, et al.
0

Similarity between objects is multi-faceted and it can be easier for human annotators to measure it when the focus is on a specific aspect. We consider the problem of mapping objects into view-specific embeddings where the distance between them is consistent with the similarity comparisons of the form "from the t-th view, object A is more similar to B than to C". Our framework jointly learns view-specific embeddings exploiting correlations between views. Experiments on a number of datasets, including one of multi-view crowdsourced comparison on bird images, show the proposed method achieves lower triplet generalization error when compared to both learning embeddings independently for each view and all views pooled into one view. Our method can also be used to learn multiple measures of similarity over input features taking class labels into account and compares favorably to existing approaches for multi-task metric learning on the ISOLET dataset.

READ FULL TEXT

page 1

page 11

research
02/08/2023

Multiview Representation Learning from Crowdsourced Triplet Comparisons

Crowdsourcing has been used to collect data at scale in numerous fields....
research
10/21/2016

Multi-view metric learning for multi-instance image classification

It is critical and meaningful to make image classification since it can ...
research
03/25/2016

Conditional Similarity Networks

What makes images similar? To measure the similarity between images, the...
research
10/31/2018

Boosting for Comparison-Based Learning

We consider the problem of classification in a comparison-based setting:...
research
03/31/2017

Transfer of View-manifold Learning to Similarity Perception of Novel Objects

We develop a model of perceptual similarity judgment based on re-trainin...
research
03/26/2017

Learned Multi-Patch Similarity

Estimating a depth map from multiple views of a scene is a fundamental t...
research
11/06/2015

Active Perceptual Similarity Modeling with Auxiliary Information

Learning a model of perceptual similarity from a collection of objects i...

Please sign up or login with your details

Forgot password? Click here to reset