Contextual Visual Similarity

12/08/2016
by   Xiaofang Wang, et al.
0

Measuring visual similarity is critical for image understanding. But what makes two images similar? Most existing work on visual similarity assumes that images are similar because they contain the same object instance or category. However, the reason why images are similar is much more complex. For example, from the perspective of category, a black dog image is similar to a white dog image. However, in terms of color, a black dog image is more similar to a black horse image than the white dog image. This example serves to illustrate that visual similarity is ambiguous but can be made precise when given an explicit contextual perspective. Based on this observation, we propose the concept of contextual visual similarity. To be concrete, we examine the concept of contextual visual similarity in the application domain of image search. Instead of providing only a single image for image similarity search (, Google image search), we require three images. Given a query image, a second positive image and a third negative image, dissimilar to the first two images, we define a contextualized similarity search criteria. In particular, we learn feature weights over all the feature dimensions of each image such that the distance between the query image and the positive image is small and their distances to the negative image are large after reweighting their features. The learned feature weights encode the contextualized visual similarity specified by the user and can be used for attribute specific image search. We also show the usefulness of our contextualized similarity weighting scheme for different tasks, such as answering visual analogy questions and unsupervised attribute discovery.

READ FULL TEXT
research
12/07/2018

Interval type-2 Beta Fuzzy Near set based approach to content based image retrieval

In an automated search system, similarity is a key concept in solving a ...
research
05/24/2023

SUVR: A Search-based Approach to Unsupervised Visual Representation Learning

Unsupervised learning has grown in popularity because of the difficulty ...
research
04/11/2011

GEOMIR2K9 - A Similar Scene Finder

The main goal of the GEOMIR2K9 project is to create a software program t...
research
09/24/2018

Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback

In this paper, we introduce an attribute-based interactive image search ...
research
09/07/2016

Automatic Visual Theme Discovery from Joint Image and Text Corpora

A popular approach to semantic image understanding is to manually tag im...
research
03/06/2019

Camera Obscurer: Generative Art for Design Inspiration

We investigate using generated decorative art as a source of inspiration...
research
10/14/2019

Real-Time Visual Navigation in Huge Image Sets Using Similarity Graphs

Nowadays stock photo agencies often have millions of images. Non-stop vi...

Please sign up or login with your details

Forgot password? Click here to reset