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

In object detection, bounding box regression (BBR) is a crucial step thatdetermines the object localization performance. However, we find that mostprevious loss functions for BBR have two main drawbacks: (i) Both $\ell_n$-normand IOU-based loss functions are inefficient to depict the objective of BBR,which leads to slow convergence and inaccurate regression results. (ii) Most ofthe loss functions ignore the imbalance problem in BBR that the large number ofanchor boxes which have small overlaps with the target boxes contribute most tothe optimization of BBR. To mitigate the adverse effects caused thereby, weperform thorough studies to exploit the potential of BBR losses in this paper.Firstly, an Efficient Intersection over Union (EIOU) loss is proposed, whichexplicitly measures the discrepancies of three geometric factors in BBR, i.e.,the overlap area, the central point and the side length. After that, we statethe Effective Example Mining (EEM) problem and propose a regression version offocal loss to make the regression process focus on high-quality anchor boxes.Finally, the above two parts are combined to obtain a new loss function, namelyFocal-EIOU loss. Extensive experiments on both synthetic and real datasets areperformed. Notable superiorities on both the convergence speed and thelocalization accuracy can be achieved over other BBR losses.

Focal and Efficient IOU Loss for Accurate Bounding Box Regression