Excitation Dropout: Encouraging Plasticity in Deep Neural Networks
This addresses the problem of overfitting and inefficient network usage in deep learning for computer vision, though it is incremental as it builds on existing dropout methods.
The paper tackles the problem of improving generalization and resilience in deep neural networks by introducing a guided dropout regularizer that drops high-saliency neurons with higher probability, forcing the network to learn alternative paths. The result is demonstrated through better generalization, increased neuron utilization, and higher resilience to compression across four image/video recognition benchmarks.
We propose a guided dropout regularizer for deep networks based on the evidence of a network prediction defined as the firing of neurons in specific paths. In this work, we utilize the evidence at each neuron to determine the probability of dropout, rather than dropping out neurons uniformly at random as in standard dropout. In essence, we dropout with higher probability those neurons which contribute more to decision making at training time. This approach penalizes high saliency neurons that are most relevant for model prediction, i.e. those having stronger evidence. By dropping such high-saliency neurons, the network is forced to learn alternative paths in order to maintain loss minimization, resulting in a plasticity-like behavior, a characteristic of human brains too. We demonstrate better generalization ability, an increased utilization of network neurons, and a higher resilience to network compression using several metrics over four image/video recognition benchmarks.