Patent · US Active

Instance-weighted mixture modeling to enhance training collections for image annotation

US9646226B2 · kind B2 · utility

8Cited by
6References
10Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 16, 2014
Grant dateMay 9, 2017
Priority date
Expiry dateJun 14, 2035

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F18/214
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Automatic selection of training images is enhanced using an instance-weighted mixture modeling framework called ARTEMIS. An optimization algorithm is derived that in addition to mixture parameter estimation learns instance-weights, essentially adapting to the noise associated with each example. The mechanism of hypothetical local mapping is evoked so that data in diverse mathematical forms or modalities can be cohesively treated as the system maintains tractability in optimization. Training examples are selected from top-ranked images of a likelihood-based image ranking. Experiments indicate that ARTEMIS exhibits higher resilience to noise than several baselines for large training data collection. The performance of ARTEMIS-trained image annotation system is comparable to using manually curated datasets.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.