Gradient Driven Learning for Pooling in Visual Pipeline Feature Extraction Models
This work addresses a specific bottleneck in visual recognition models for researchers, but it is incremental as it builds on existing pipeline methods.
The paper tackles the problem of hyper-parameter selection in visual pipeline feature extraction models by reformulating pooling as a function of adjustable weight parameters and using supervised gradient descent to tune these maps, resulting in moderate gains in classification accuracy.
Hyper-parameter selection remains a daunting task when building a pattern recognition architecture which performs well, particularly in recently constructed visual pipeline models for feature extraction. We re-formulate pooling in an existing pipeline as a function of adjustable pooling map weight parameters and propose the use of supervised error signals from gradient descent to tune the established maps within the model. This technique allows us to learn what would otherwise be a design choice within the model and specialize the maps to aggregate areas of invariance for the task presented. Preliminary results show moderate potential gains in classification accuracy and highlight areas of importance within the intermediate feature representation space.