Learning Everything about Anything: Webly-Supervised Visual Concept Learning

@article{Divvala2014LearningEA,
  title={Learning Everything about Anything: Webly-Supervised Visual Concept Learning},
  author={S. Divvala and Ali Farhadi and Carlos Guestrin},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={3270-3277}
}
  • S. Divvala, Ali Farhadi, Carlos Guestrin
  • Published 2014
  • Computer Science
  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • Recognition is graduating from labs to real-world applications. While it is encouraging to see its potential being tapped, it brings forth a fundamental challenge to the vision researcher: scalability. How can we learn a model for any concept that exhaustively covers all its appearance variations, while requiring minimal or no human supervision for compiling the vocabulary of visual variance, gathering the training images and annotations, and learning the models? In this paper, we introduce a… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Semantic Attributes for Transfer Learning in Visual Recognition
    Relaxing from Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging
    • 33
    • PDF
    Supervision Beyond Manual Annotations for Learning Visual Representations
    • 5
    • PDF
    What's in a Question: Using Visual Questions as a Form of Supervision
    • 13
    • PDF
    Discovering and Leveraging Visual Structure for Large-Scale Recognation
    Learning to Learn from Noisy Web Videos
    • 20
    • PDF
    Online Collaborative Learning for Open-Vocabulary Visual Classifiers
    • 38
    • PDF
    Sherlock: Modeling Structured Knowledge in Images

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 53 REFERENCES
    What helps where – and why? Semantic relatedness for knowledge transfer
    • 284
    • PDF
    OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning
    • 325
    • PDF
    Large-scale live active learning: Training object detectors with crawled data and crowds
    • 142
    • PDF
    Learning to detect unseen object classes by between-class attribute transfer
    • 1,620
    • Highly Influential
    • PDF
    Exploiting weakly-labeled Web images to improve object classification: a domain adaptation approach
    • 228
    • PDF
    Learning Object Categories From Internet Image Searches
    • 70
    • PDF
    Composing Simple Image Descriptions using Web-scale N-grams
    • 264
    • PDF
    Describing objects by their attributes
    • 1,582
    • PDF