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

One-stage object detectors such as SSD or YOLO already have shown promisingaccuracy with small memory footprint and fast speed. However, it is widelyrecognized that one-stage detectors have difficulty in detecting small objectswhile they are competitive with two-stage methods on large objects. In thispaper, we investigate how to alleviate this problem starting from the SSDframework. Due to their pyramidal design, the lower layer that is responsiblefor small objects lacks strong semantics(e.g contextual information). Weaddress this problem by introducing a feature combining module that spreads outthe strong semantics in a top-down manner. Our final model StairNet detectorunifies the multi-scale representations and semantic distribution effectively.Experiments on PASCAL VOC 2007 and PASCAL VOC 2012 datasets demonstrate thatStairNet significantly improves the weakness of SSD and outperforms the otherstate-of-the-art one-stage detectors.

StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection