A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2202.09741v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Visual Attention Network
[article]
<span title="2022-03-08">2022</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2022-02-20">2022</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.09741v1">arXiv:2202.09741v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uu67xikin5hidlwy57bcunteiu">fatcat:uu67xikin5hidlwy57bcunteiu</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.09741v1">arXiv:2202.09741v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uu67xikin5hidlwy57bcunteiu">fatcat:uu67xikin5hidlwy57bcunteiu</a> </span>
<span title="2022-03-03">2022</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.09741v2">arXiv:2202.09741v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cqndcaxg7ncihfqkr3lnkch7dy">fatcat:cqndcaxg7ncihfqkr3lnkch7dy</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.09741v2">arXiv:2202.09741v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cqndcaxg7ncihfqkr3lnkch7dy">fatcat:cqndcaxg7ncihfqkr3lnkch7dy</a> </span>
While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in computer vision. (1) Treating images as 1D sequences neglects their 2D structures. (2) The quadratic complexity is too expensive for high-resolution images. (3) It only captures spatial adaptability but ignores channel adaptability. In this paper, we propose
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.09741v3">arXiv:2202.09741v3</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gqlascuu5vfwho73wy2msg4pym">fatcat:gqlascuu5vfwho73wy2msg4pym</a>
</span>
more »
... a novel large kernel attention (LKA) module to enable self-adaptive and long-range correlations in self-attention while avoiding the above issues. We further introduce a novel neural network based on LKA, namely Visual Attention Network (VAN). While extremely simple, VAN outperforms the state-of-the-art vision transformers and convolutional neural networks with a large margin in extensive experiments, including image classification, object detection, semantic segmentation, instance segmentation, etc. Code is available at https://github.com/Visual-Attention-Network.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220310003401/https://arxiv.org/pdf/2202.09741v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/47/78/4778413e77ba6ad9b8feee7a91ced1ecae23bec0.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.09741v3" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>