Learning Concept Embeddings with Combined Human-Machine Expertise
arXiv:1509.07479
Abstract
This paper presents our work on "SNaCK," a low-dimensional concept embedding algorithm that combines human expertise with automatic machine similarity kernels. Both parts are complimentary: human insight can capture relationships that are not apparent from the object's visual similarity and the machine can help relieve the human from having to exhaustively specify many constraints. We show that our SNaCK embeddings are useful in several tasks: distinguishing prime and nonprime numbers on MNIST, discovering labeling mistakes in the Caltech UCSD Birds (CUB) dataset with the help of deep-learned features, creating training datasets for bird classifiers, capturing subjective human taste on a new dataset of 10,000 foods, and qualitatively exploring an unstructured set of pictographic characters. Comparisons with the state-of-the-art in these tasks show that SNaCK produces better concept embeddings that require less human supervision than the leading methods.
To appear at ICCV 2015. (This version has updated author affiliations and updated footnotes.)
References in corpus (5)
- Efficient Estimation of Word Representations in Vector Space
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
- Learning Fine-grained Image Similarity with Deep Ranking
- Jointly Learning Multiple Measures of Similarities from Triplet Comparisons
Cited by in corpus (4)
- Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification
- Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking
- It's just a matter of perspective(s): Crowd-Powered Consensus Organization of Corpora
- Less but Better: Generalization Enhancement of Ordinal Embedding via Distributional Margin