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

The fully convolutional network (FCN) has dominated salient object detectionfor a long period. However, the locality of CNN requires the model deep enoughto have a global receptive field and such a deep model always leads to the lossof local details. In this paper, we introduce a new attention-based encoder,vision transformer, into salient object detection to ensure the globalizationof the representations from shallow to deep layers. With the global view invery shallow layers, the transformer encoder preserves more localrepresentations to recover the spatial details in final saliency maps. Besides,as each layer can capture a global view of its previous layer, adjacent layerscan implicitly maximize the representation differences and minimize theredundant features, making that every output feature of transformer layerscontributes uniquely for final prediction. To decode features from thetransformer, we propose a simple yet effective deeply-transformed decoder. Thedecoder densely decodes and upsamples the transformer features, generating thefinal saliency map with less noise injection. Experimental results demonstratethat our method significantly outperforms other FCN-based and transformer-basedmethods in five benchmarks by a large margin, with an average of 12.17%improvement in terms of Mean Absolute Error (MAE). Code will be available athttps://github.com/OliverRensu/GLSTR.

Unifying Global-Local Representations in Salient Object Detection with Transformer