On Intra-Class Variance for Deep Learning of Classifiers
2019
scientific article
english
- deep learning of image classifier
- convolutional neural network
- Shanon information measure
- intra-class variance
- image embedding
EN A novel technique for deep learning of image classifiers is presented. The learned CNN models higher offer better separation of deep features (also known as embedded vectors) measured by Euclidean proximity and also no deterioration of the classification results by class membership probability. The latter feature can be used for enhancing image classifiers having the classes at the model’s exploiting stage different from from classes during the training stage. While the Shannon information of SoftMax probability for target class is extended for mini-batch by the intra-class variance, the trained network itself is extended by the Hadamard layer with the pa-rameters representing the class centers. Contrary to the existing solutions, this extra neural layer enables interfacing of the training algorithm to the standard stochastic gradient optimizers, e.g. AdaM algorithm. Moreover, this approach makes the computed centroids immediately adapting to the updating embedded vectors and finally getting the comparable accuracy in less epochs.
285 - 301
CC BY-NC-ND (attribution - noncommercial - no derivatives)
public
20
40