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/

Zendy Plus

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

Zendy Tools

Zendy Open

We consider the problem of integrating non-imaging information intosegmentation networks to improve performance. Conditioning layers such as FiLMprovide the means to selectively amplify or suppress the contribution ofdifferent feature maps in a linear fashion. However, spatial dependency isdifficult to learn within a convolutional paradigm. In this paper, we propose amechanism to allow for spatial localisation conditioned on non-imaginginformation, using a feature-wise attention mechanism comprising adifferentiable parametrised function (e.g. Gaussian), prior to applying thefeature-wise modulation. We name our method INstance modulation with SpatIalDEpendency (INSIDE). The conditioning information might comprise any factorsthat relate to spatial or spatio-temporal information such as lesion location,size, and cardiac cycle phase. Our method can be trained end-to-end and doesnot require additional supervision. We evaluate the method on two datasets: anew CLEVR-Seg dataset where we segment objects based on location, and the ACDCdataset conditioned on cardiac phase and slice location within the volume. Codeand the CLEVR-Seg dataset are available at https://github.com/jacenkow/inside.

INSIDE: Steering Spatial Attention with Non-Imaging Information in CNNs