Activate or Not: Learning Customized Activation
This work addresses the need for more effective and adaptable activation functions across various deep learning tasks, offering a novel approach that enhances performance in image classification, object detection, and semantic segmentation.
The paper tackles the problem of designing activation functions in neural networks by introducing ACON, a learnable activation that generalizes Swish and Maxout, achieving improvements such as a 6.7% increase in ImageNet top-1 accuracy on MobileNet-0.25 and 1.8% on ResNet-152.
We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not. Interestingly, we find Swish, the recent popular NAS-searched activation, can be interpreted as a smooth approximation to ReLU. Intuitively, in the same way, we approximate the more general Maxout family to our novel ACON family, which remarkably improves the performance and makes Swish a special case of ACON. Next, we present meta-ACON, which explicitly learns to optimize the parameter switching between non-linear (activate) and linear (inactivate) and provides a new design space. By simply changing the activation function, we show its effectiveness on both small models and highly optimized large models (e.g. it improves the ImageNet top-1 accuracy rate by 6.7% and 1.8% on MobileNet-0.25 and ResNet-152, respectively). Moreover, our novel ACON can be naturally transferred to object detection and semantic segmentation, showing that ACON is an effective alternative in a variety of tasks. Code is available at https://github.com/nmaac/acon.