TR2018-033

Neural Algebra of Classifiers


    •  Santa Cruz, R., Fernando, B., Cherian, A., Gould, S., "Neural Algebra of Classifiers", IEEE Winter Conference on Applications of Computer Vision (WACV), DOI: 10.1109/​WACV.2018.00085, March 2018, pp. 729-737.
      BibTeX TR2018-033 PDF
      • @inproceedings{Santacruz2018mar,
      • author = {Santa Cruz, Rodrigo and Fernando, Basura and Cherian, Anoop and Gould, Stephen},
      • title = {Neural Algebra of Classifiers},
      • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
      • year = 2018,
      • pages = {729--737},
      • month = mar,
      • doi = {10.1109/WACV.2018.00085},
      • url = {https://www.merl.com/publications/TR2018-033}
      • }
  • MERL Contact:
  • Research Areas:

    Artificial Intelligence, Computer Vision, Machine Learning

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.