Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction

@article{Zhang2013DeformablePD,
  title={Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction},
  author={Ning Zhang and Ryan Farrell and Forrest N. Iandola and Trevor Darrell},
  journal={2013 IEEE International Conference on Computer Vision},
  year={2013},
  pages={729-736}
}
Recognizing objects in fine-grained domains can be extremely challenging due to the subtle differences between subcategories. Discriminative markings are often highly localized, leading traditional object recognition approaches to struggle with the large pose variation often present in these domains. Pose-normalization seeks to align training exemplars, either piecewise by part or globally for the whole object, effectively factoring out differences in pose and in viewing angle. Prior approaches… CONTINUE READING

Similar Papers

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

Key Quantitative Results

  • Our DPD-strong achieves 50.05% mean accuracy and DPD-weak achieves 50.98% on this dataset, outperforming other state-of-art methods.

Citations

Publications citing this paper.
SHOWING 1-10 OF 164 CITATIONS

The application of two-level attention models in deep convolutional neural network for fine-grained image classification

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2014
VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Visual Representations for Fine-grained Categorization

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops
  • 2014
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Nonparametric Part Transfer for Fine-Grained Recognition

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Image context for object detection, object context for part detection

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Learning Semantic Part-Based Models from Google Images

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2018
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Webly-Supervised Fine-Grained Visual Categorization via Deep Domain Adaptation

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2018
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Learning to Classify Fine-Grained Categories with Privileged Visual-Semantic Misalignment

  • IEEE Transactions on Big Data
  • 2017
VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Fine-grained classification via mixture of deep convolutional neural networks

  • 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2015
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2013
2019

CITATION STATISTICS

  • 15 Highly Influenced Citations

  • Averaged 22 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 47 REFERENCES

POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Pose pooling kernels for sub-category recognition

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Fine-Grained Crowdsourcing for Fine-Grained Recognition

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

Cats and dogs

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance

  • 2011 International Conference on Computer Vision
  • 2011
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Describing people: A poselet-based approach to attribute classification

  • 2011 International Conference on Computer Vision
  • 2011
VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL