Learning Universal Embeddings from Attributes

@inproceedings{Nigam2018LearningUE,
  title={Learning Universal Embeddings from Attributes},
  author={Ishan Nigam and Cheng Huang and Deva Ramanan},
  year={2018}
}
We address the problem of learning a universal embedding space from which different semantic concepts or notions of similarity can originate. Contemporary attribute datasets provide rich multi-label annotations to achieve this goal. Universal embeddings learned from the multi-label attributes would naturally encourage feature sharing, leading to reduced feature redundancy and boosted generalization ability. This paper presents a multi-task framework to learn universal embeddings by mapping them… CONTINUE READING

Figures and Tables from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

Conditional Similarity Networks

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Sampling Matters in Deep Embedding Learning

R. Manmatha, Chao-Yuan Wu, Alexander J. Smola, Philipp Krahenbuhl
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

FaceNet: A unified embedding for face recognition and clustering

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Deep Learning Face Attributes in the Wild

  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2014
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

PANDA: Pose Aligned Networks for Deep Attribute Modeling

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 1 EXCERPT