GAAF: Searching Activation Functions for Binary Neural Networks through Genetic Algorithm
This addresses the accuracy gap in BNNs for cost and power-restricted domains like edge devices, offering a novel design approach, though it is incremental as it builds on existing BNN methods.
The paper tackles the performance degradation in binary neural networks (BNNs) by proposing a genetic algorithm to search for complementary activation functions, identifying 15 novel functions that improve accuracy by up to 2.54% on ImageNet.
Binary neural networks (BNNs) show promising utilization in cost and power-restricted domains such as edge devices and mobile systems. This is due to its significantly less computation and storage demand, but at the cost of degraded performance. To close the accuracy gap, in this paper we propose to add a complementary activation function (AF) ahead of the sign based binarization, and rely on the genetic algorithm (GA) to automatically search for the ideal AFs. These AFs can help extract extra information from the input data in the forward pass, while allowing improved gradient approximation in the backward pass. Fifteen novel AFs are identified through our GA-based search, while most of them show improved performance (up to 2.54% on ImageNet) when testing on different datasets and network models. Our method offers a novel approach for designing general and application-specific BNN architecture. Our code is available at http://github.com/flying-Yan/GAAF.