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

The loss function for bounding box regression (BBR) is essential to objectdetection. Its good definition will bring significant performance improvementto the model. Most existing works assume that the examples in the training dataare high-quality and focus on strengthening the fitting ability of BBR loss. Ifwe blindly strengthen BBR on low-quality examples, it will jeopardizelocalization performance. Focal-EIoU v1 was proposed to solve this problem, butdue to its static focusing mechanism (FM), the potential of non-monotonic FMwas not fully exploited. Based on this idea, we propose an IoU-based loss witha dynamic non-monotonic FM named Wise-IoU (WIoU). The dynamic non-monotonic FMuses the outlier degree instead of IoU to evaluate the quality of anchor boxesand provides a wise gradient gain allocation strategy. This strategy reducesthe competitiveness of high-quality anchor boxes while also reducing theharmful gradient generated by low-quality examples. This allows WIoU to focuson ordinary-quality anchor boxes and improve the detector's overallperformance. When WIoU is applied to the state-of-the-art real-time detectorYOLOv7, the AP-75 on the MS-COCO dataset is improved from 53.03% to 54.50%.Code is available at https://github.com/Instinct323/wiou.

Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism