Viet-Anh on Software Logo

What is: HaloNet?

SourceScaling Local Self-Attention for Parameter Efficient Visual Backbones
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

A HaloNet is a self-attention based model for efficient image classification. It relies on a local self-attention architecture that efficiently maps to existing hardware with haloing. The formulation breaks translational equivariance, but the authors observe that it improves throughput and accuracies over the centered local self-attention used in regular self-attention. The approach also utilises a strided self-attentive downsampling operation for multi-scale feature extraction.