Neural algebra of classifiers

Rodrigo Santa Cruz, Basura Fernando, Anoop Cherian, Stephen Gould

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    6 Citations (Scopus)

    Abstract

    The world is fundamentally compositional, so it is natural to think of visual recognition as the recognition of basic visually primitives that are composed according to well-defined rules. This strategy allows us to recognize unseen complex concepts from simple visual primitives. However, the current trend in visual recognition follows a data greedy approach where huge amounts of data are required to learn models for any desired visual concept. In this paper, we build on the compositionality principle and develop an 'algebra' to compose classifiers for complex visual concepts. To this end, we learn neural network modules to perform boolean algebra operations on simple visual classifiers. Since these modules form a complete functional set, a classifier for any complex visual concept defined as a boolean expression of primitives can be obtained by recursively applying the learned modules, even if we do not have a single training sample. As our experiments show, using such a framework, we can compose classifiers for complex visual concepts outperforming standard baselines on two well-known visual recognition benchmarks. Finally, we present a qualitative analysis of our method and its properties.

    Original languageEnglish
    Title of host publicationProceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages729-737
    Number of pages9
    ISBN (Electronic)9781538648865
    DOIs
    Publication statusPublished - 3 May 2018
    Event18th IEEE Winter Conference on Applications of Computer Vision, WACV 2018 - Lake Tahoe, United States
    Duration: 12 Mar 201815 Mar 2018

    Publication series

    NameProceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018
    Volume2018-January

    Conference

    Conference18th IEEE Winter Conference on Applications of Computer Vision, WACV 2018
    Country/TerritoryUnited States
    CityLake Tahoe
    Period12/03/1815/03/18

    Fingerprint

    Dive into the research topics of 'Neural algebra of classifiers'. Together they form a unique fingerprint.

    Cite this