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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Existing RGB-D SOD methods mainly rely on a symmetric two-stream CNN-basednetwork to extract RGB and depth channel features separately. However, thereare two problems with the symmetric conventional network structure: first, theability of CNN in learning global contexts is limited; second, the symmetrictwo-stream structure ignores the inherent differences between modalities. Inthis paper, we propose a Transformer-based asymmetric network (TANet) to tacklethe issues mentioned above. We employ the powerful feature extractioncapability of Transformer (PVTv2) to extract global semantic information fromRGB data and design a lightweight CNN backbone (LWDepthNet) to extract spatialstructure information from depth data without pre-training. The asymmetrichybrid encoder (AHE) effectively reduces the number of parameters in the modelwhile increasing speed without sacrificing performance. Then, we design across-modal feature fusion module (CMFFM), which enhances and fuses RGB anddepth features with each other. Finally, we add edge prediction as an auxiliarytask and propose an edge enhancement module (EEM) to generate sharper contours.Extensive experiments demonstrate that our method achieves superior performanceover 14 state-of-the-art RGB-D methods on six public datasets. Our code will bereleased at https://github.com/lc012463/TANet.

TANet: Transformer-based Asymmetric Network for RGB-D Salient Object Detection