Corpus ID: 14403330

Automatic Discovery and Optimization of Parts for Image Classification

@article{Parizi2015AutomaticDA,
  title={Automatic Discovery and Optimization of Parts for Image Classification},
  author={S. N. Parizi and A. Vedaldi and Andrew Zisserman and Pedro F. Felzenszwalb},
  journal={CoRR},
  year={2015},
  volume={abs/1412.6598}
}
Part-based representations have been shown to be very useful for image classification. Learning part-based models is often viewed as a two-stage problem. First, a collection of informative parts is discovered, using heuristics that promote part distinctiveness and diversity, and then classifiers are trained on the vector of part responses. In this paper we unify the two stages and learn the image classifiers and a set of shared parts jointly. We generate an initial pool of parts by randomly… Expand
Unsupervised Part Learning for Visual Recognition
SPLeaP: Soft Pooling of Learned Parts for Image Classification
Ensemble of Part Detectors for Simultaneous Classification and Localization
No spare parts: Sharing part detectors for image categorization
Learning Dictionary of Discriminative Part Detectors for Image Categorization and Cosegmentation
  • J. Sun, J. Ponce
  • Mathematics, Computer Science
  • International Journal of Computer Vision
  • 2016
Automatic Discovery of Discriminative Parts as a Quadratic Assignment Problem
Discriminative part model for visual recognition
Learning Multi-Instance Deep Discriminative Patterns for Image Classification
Unsupervised learning of discriminative representation for image recognition
  • 2019
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 23 REFERENCES
Blocks That Shout: Distinctive Parts for Scene Classification
Object Detection with Discriminatively Trained Part Based Models
Learning Discriminative Part Detectors for Image Classification and Cosegmentation
  • J. Sun, J. Ponce
  • Computer Science
  • 2013 IEEE International Conference on Computer Vision
  • 2013
Learning Collections of Part Models for Object Recognition
Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognition
Unsupervised Discovery of Mid-Level Discriminative Patches
Training Deformable Part Models with Decorrelated Features
Reconfigurable models for scene recognition
Discriminative Decorrelation for Clustering and Classification
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
...
1
2
3
...