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

Two-stage deep object detectors generate a set of regions-of-interest (RoI)in the first stage, then, in the second stage, identify objects among theproposed RoIs that sufficiently overlap with a ground truth (GT) box. Thesecond stage is known to suffer from a bias towards RoIs that have lowintersection-over-union (IoU) with the associated GT boxes. To address thisissue, we first propose a sampling method to generate bounding boxes (BB) thatoverlap with a given reference box more than a given IoU threshold. Then, weuse this BB generation method to develop a positive RoI (pRoI) generator thatproduces RoIs following any desired spatial or IoU distribution, for thesecond-stage. We show that our pRoI generator is able to simulate othersampling methods for positive examples such as hard example mining and primesampling. Using our generator as an analysis tool, we show that (i) IoUimbalance has an adverse effect on performance, (ii) hard positive examplemining improves the performance only for certain input IoU distributions, and(iii) the imbalance among the foreground classes has an adverse effect onperformance and that it can be alleviated at the batch level. Finally, we trainFaster R-CNN using our pRoI generator and, compared to conventional training,obtain better or on-par performance for low IoUs and significant improvementswhen trained for higher IoUs for Pascal VOC and MS COCO datasets. The code isavailable at: https://github.com/kemaloksuz/BoundingBoxGenerator.

Generating Positive Bounding Boxes for Balanced Training of Object Detectors