Name
Abstract | ||
|---|---|---|
Fisher-Vectors (FV) encode higher-order statistics of a set of multiple local descriptors like SIFT features. They already show good performance in combination with shallow learning architectures on visual recognitions tasks. Current methods using FV as a feature descriptor in deep architectures assume that all original input features are static. We propose a framework to jointly learn the representation of original features, FV parameters and parameters of the classifier in the style of traditional neural networks. Our proof of concept implementation improves the performance of FV on the Pascal Voc 2007 challenge in a multi-GPU setting in comparison to a default SVM setting. We demonstrate that FV can be embedded into neural networks at arbitrary positions, allowing end-to-end training with back-propagation. |
Year | Venue | Field |
|---|---|---|
2017 | arXiv: Computer Vision and Pattern Recognition | Scale-invariant feature transform,ENCODE,Fisher vector,Pattern recognition,CUDA,Computer science,Support vector machine,Artificial intelligence,Artificial neural network,Classifier (linguistics),Backpropagation,Machine learning |
DocType | Volume | Citations |
Journal | abs/1702.02549 | 0 |
PageRank | References | Authors |
0.34 | 7 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Patrick Wieschollek | 1 | 26 | 3.21 |
| Fabian Groh | 2 | 7 | 2.09 |
| Hendrik P. A. Lensch | 3 | 1471 | 96.59 |