VeLU: Variance-enhanced Learning Unit for Deep Neural Networks
This work addresses optimization stability and generalization in deep learning for vision tasks, but it appears incremental as it builds on existing activation functions with specific enhancements.
The authors tackled the problem of activation functions in deep neural networks, which suffer from issues like vanishing gradients and lack of adaptability, by proposing VeLU, a variance-enhanced activation function that dynamically scales based on input variance; experiments on multiple models and benchmarks showed VeLU's superiority over existing functions like ReLU and Swish.
Activation functions are fundamental in deep neural networks and directly impact gradient flow, optimization stability, and generalization. Although ReLU remains standard because of its simplicity, it suffers from vanishing gradients and lacks adaptability. Alternatives like Swish and GELU introduce smooth transitions, but fail to dynamically adjust to input statistics. We propose VeLU, a Variance-enhanced Learning Unit as an activation function that dynamically scales based on input variance by integrating ArcTan-Sin transformations and Wasserstein-2 regularization, effectively mitigating covariate shifts and stabilizing optimization. Extensive experiments on ViT_B16, VGG19, ResNet50, DenseNet121, MobileNetV2, and EfficientNetB3 confirm VeLU's superiority over ReLU, ReLU6, Swish, and GELU on six vision benchmarks. The codes of VeLU are publicly available on GitHub.