# Lightweight Structure-Aware Attention for Visual Understanding Source: [Lightweight Structure-Aware Attention for Visual Understanding]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:04:38.175Z Authors: Heeseung Kwon, Francisco M. Castro, Manuel J. Marin-Jimenez, Nicolas Guil, Karteek Alahari Published: 2022-11-29T15:20:14.000Z ## Abstract Attention operator has been widely used as a basic brick in visual understanding since it provides some flexibility through its adjustable kernels. However, this operator suffers from inherent limitations: (1) the attention kernel is not discriminative enough, resulting in high redundancy, and (2) the complexity in computation and memory is quadratic in the sequence length. In this paper, we propose a novel attention operator, called Lightweight Structure-aware Attention (LiSA), which has a better representation power with log-linear complexity. Our operator transforms the attention kernels to be more discriminative by learning structural patterns. These structural patterns are encoded by exploiting a set of relative position embeddings (RPEs) as multiplicative weights, thereby improving the representation power of the attention kernels. Additionally, the RPEs are approximated to obtain log-linear complexity. Our experiments and analyses demonstrate that the proposed operator outperforms self-attention and other existing operators, achieving state-of-the-art results on ImageNet-1K and other downstream tasks such as video action recognition on Kinetics-400, object detection \\& instance segmentation on COCO, and semantic segmentation on ADE-20K. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()