# Adaptive Attention Span in Computer Vision

Source: [Adaptive Attention Span in Computer Vision](<https://www.sota2.com/research/paper/68fa675b1e209131cea15c9a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:01:46.445Z

Authors: Jerrod Parker, Shakti Kumar, Joe Roussy

Published: 2020-04-18T21:32:47.000Z

## Abstract

Recent developments in Transformers for language modeling have opened new areas of research in computer vision. Results from late 2019 showed vast performance increases in both object detection and recognition when convolutions are replaced by local self-attention kernels. Models using local self-attention kernels were also shown to have less parameters and FLOPS compared to equivalent architectures that only use convolutions. In this work we propose a novel method for learning the local self-attention kernel size. We then compare its performance to fixed-size local attention and convolution kernels. The code for all our experiments and models is available at https://github.com/JoeRoussy/adaptive-attention-in-cv

## 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](<https://arxiv.org/abs/2004.08708>)

[PDF](<https://arxiv.org/pdf/2004.08708.pdf>)
