AFN: Adaptive Fusion Normalization via an Encoder-Decoder Framework
This work addresses a foundational issue in deep learning by improving normalization layers, but it appears incremental as it builds on existing normalization methods.
The paper tackles the problem of designing a unified normalization function to combine advantages and mitigate weaknesses of existing normalization layers, proposing Adaptive Fusion Normalization (AFN) which outperforms previous techniques in domain generalization and image classification tasks.
The success of deep learning is inseparable from normalization layers. Researchers have proposed various normalization functions, and each of them has both advantages and disadvantages. In response, efforts have been made to design a unified normalization function that combines all normalization procedures and mitigates their weaknesses. We also proposed a new normalization function called Adaptive Fusion Normalization. Through experiments, we demonstrate AFN outperforms the previous normalization techniques in domain generalization and image classification tasks.