English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper addresses the problem of very large-scale image retrieval,focusing on improving its accuracy and robustness. We target enhancedrobustness of search to factors such as variations in illumination, objectappearance and scale, partial occlusions, and cluttered backgrounds -particularly important when search is performed across very large datasets withsignificant variability. We propose a novel CNN-based global descriptor, calledREMAP, which learns and aggregates a hierarchy of deep features from multipleCNN layers, and is trained end-to-end with a triplet loss. REMAP explicitlylearns discriminative features which are mutually-supportive and complementaryat various semantic levels of visual abstraction. These dense local featuresare max-pooled spatially at each layer, within multi-scale overlapping regions,before aggregation into a single image-level descriptor. To identify thesemantically useful regions and layers for retrieval, we propose to measure theinformation gain of each region and layer using KL-divergence. Our systemeffectively learns during training how useful various regions and layers areand weights them accordingly. We show that such relative entropy-guidedaggregation outperforms classical CNN-based aggregation controlled by SGD. Theentire framework is trained in an end-to-end fashion, outperforming the lateststate-of-the-art results. On image retrieval datasets Holidays, Oxford andMPEG, the REMAP descriptor achieves mAP of 95.5%, 91.5%, and 80.1%respectively, outperforming any results published to date. REMAP also formedthe core of the winning submission to the Google Landmark Retrieval Challengeon Kaggle.

REMAP: Multi-layer entropy-guided pooling of dense CNN features for image retrieval