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

Recently two-stage detectors have surged ahead of single-shot detectors inthe accuracy-vs-speed trade-off. Nevertheless single-shot detectors areimmensely popular in embedded vision applications. This paper bringssingle-shot detectors up to the same level as current two-stage techniques. Wedo this by improving training for the state-of-the-art single-shot detector,RetinaNet, in three ways: integrating instance mask prediction for the firsttime, making the loss function adaptive and more stable, and includingadditional hard examples in training. We call the resulting augmented networkRetinaMask. The detection component of RetinaMask has the same computationalcost as the original RetinaNet, but is more accurate. COCO test-dev results areup to 41.4 mAP for RetinaMask-101 vs 39.1mAP for RetinaNet-101, while theruntime is the same during evaluation. Adding Group Normalization increases theperformance of RetinaMask-101 to 41.7 mAP. Code isat:https://github.com/chengyangfu/retinamask

RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free