Learning Joint Feature Adaptation for Zero-Shot Recognition

@article{Zhang2016LearningJF,
  title={Learning Joint Feature Adaptation for Zero-Shot Recognition},
  author={Ziming Zhang and Venkatesh Saligrama},
  journal={CoRR},
  year={2016},
  volume={abs/1611.07593}
}
Zero-shot recognition (ZSR) aims to recognize targetdomain data instances of unseen classes based on the models learned from associated pairs of seen-class source and target domain data. One of the key challenges in ZSR is the relative scarcity of source-domain features (e.g. one feature vector per class), which do not fully account for wide variability in target-domain instances. In this paper we propose a novel framework of learning data-dependent feature transforms for scoring similarity… CONTINUE READING
11
Twitter Mentions

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • For instance, on aP&Y dataset we can achieve 80.89% in terms of recognition accuracy, outperforming the state-of-the-art by 11.15%.

Citations

Publications citing this paper.
SHOWING 1-5 OF 5 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 58 REFERENCES

Zero-Shot Learning via Joint Latent Similarity Embedding

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Evaluation of output embeddings for fine-grained image classification

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Label-Embedding for Attribute-Based Classification

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Fast Zero-Shot Image Tagging

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 1 EXCERPT

Latent Embeddings for Zero-Shot Classification

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 2 EXCERPTS

Less is More: Zero-Shot Learning from Online Textual Documents with Noise Suppression

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…