Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding [article]

Yang Li, Si Si, Gang Li, Cho-Jui Hsieh, Samy Bengio
2021 arXiv   pre-print
Attentional mechanisms are order-invariant. Positional encoding is a crucial component to allow attention-based deep model architectures such as Transformer to address sequences or images where the position of information matters. In this paper, we propose a novel positional encoding method based on learnable Fourier features. Instead of hard-coding each position as a token or a vector, we represent each position, which can be multi-dimensional, as a trainable encoding based on learnable
more » ... feature mapping, modulated with a multi-layer perceptron. The representation is particularly advantageous for a spatial multi-dimensional position, e.g., pixel positions on an image, where L_2 distances or more complex positional relationships need to be captured. Our experiments based on several public benchmark tasks show that our learnable Fourier feature representation for multi-dimensional positional encoding outperforms existing methods by both improving the accuracy and allowing faster convergence.
arXiv:2106.02795v3 fatcat:r64bsk7hmjdr5fibnqpvhckdua