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

Many two-stage instance segmentation heads predict a coarse 28x28 mask perinstance, which is insufficient to capture the fine-grained details of manyobjects. To address this issue, PointRend and RefineMask predict a 112x112segmentation mask resulting in higher quality segmentations. Both methodshowever have limitations by either not having access to neighboring features(PointRend) or by performing computation at all spatial locations instead ofsparsely (RefineMask). In this work, we propose EffSeg performing fine-grainedinstance segmentation in an efficient way by using our Structure-PreservingSparsity (SPS) method based on separately storing the active features, thepassive features and a dense 2D index map containing the feature indices. Thegoal of the index map is to preserve the 2D spatial configuration or structurebetween the features such that any 2D operation can still be performed. EffSegachieves similar performance on COCO compared to RefineMask, while reducing thenumber of FLOPs by 71% and increasing the FPS by 29%. Code will be released.

EffSeg: Efficient Fine-Grained Instance Segmentation using Structure-Preserving Sparsity