A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit <a rel="external noopener" href="https://www.research.ed.ac.uk/portal/files/43695374/li2017fgsa.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Synergistic Instance-Level Subspace Alignment for Fine-Grained Sketch-Based Image Retrieval
<span title="">2017</span>
<i title="Institute of Electrical and Electronics Engineers (IEEE)">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dhlhr4jqkbcmdbua2ca45o7kru" style="color: black;">IEEE Transactions on Image Processing</a>
</i>
Preserved Fulltext
We study the problem of fine-grained sketch-based image retrieval. By performing instance-level (rather than category-level) retrieval, it embodies a timely and practical application, particularly with the ubiquitous availability of touchscreens. Three factors contribute to the challenging nature of the problem: (i) free-hand sketches are inherently abstract and iconic, making visual comparisons with photos difficult, (ii) sketches and photos are in two different visual domains, i.e. black and
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2017.2745106">doi:10.1109/tip.2017.2745106</a>
<a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/28858796">pmid:28858796</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dhp2a73iyvg67kk7yu5z2x6u7m">fatcat:dhp2a73iyvg67kk7yu5z2x6u7m</a>
</span>
more »
... hite lines vs. color pixels, and (iii) fine-grained distinctions are especially challenging when executed across domain and abstraction-level. To address these challenges, we propose to bridge the image-sketch gap both at the high-level via parts and attributes, as well as at the low-level, via introducing a new domain alignment method. More specifically, (i) we contribute a dataset with 304 photos and 912 sketches, where each sketch and image is annotated with its semantic parts and associated part-level attributes. With the help of this dataset, we investigate (ii) how strongly-supervised deformable part-based models can be learned that subsequently enable automatic detection of part-level attributes, and provide pose-aligned sketch-image comparisons. To reduce the sketch-image gap when comparing low-level features, we also (iii) propose a novel method for instance-level domain-alignment, that exploits both subspace and instance-level cues to better align the domains. Finally (iv) these are combined in a matching framework integrating aligned low-level features, mid-level geometric structure and high-level semantic attributes. Extensive experiments conducted on our new dataset demonstrate effectiveness of the proposed method.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180723115336/https://www.research.ed.ac.uk/portal/files/43695374/li2017fgsa.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/f8/c8/f8c8a5f665631301ad8c7ba225ac8fe867064201.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2017.2745106">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
ieee.com
</button>
</a>