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

Current state-of-the-art weakly supervised object detection (WSOD) studiesmainly follow a two-stage training strategy which integrates a fully superviseddetector (FSD) with a pure WSOD model. There are two main problems hinderingthe performance of the two-phase WSOD approaches, i.e., insufficient learningproblem and strict reliance between the FSD and the pseudo ground truth (PGT)generated by the WSOD model. This paper proposes pseudo ground truth refinementnetwork (PGTRNet), a simple yet effective method without introducing any extralearnable parameters, to cope with these problems. PGTRNet utilizes multiplebounding boxes to establish the PGT, mitigating the insufficient learningproblem. Besides, we propose a novel online PGT refinement approach to steadilyimprove the quality of PGT by fully taking advantage of the power of FSD duringthe second-phase training, decoupling the first and second-phase models.Elaborate experiments are conducted on the PASCAL VOC 2007 benchmark to verifythe effectiveness of our methods. Experimental results demonstrate that PGTRNetboosts the backbone model by 2.1% mAP and achieves the state-of-the-artperformance.

PGTRNet: Two-phase Weakly Supervised Object Detection with Pseudo Ground Truth Refinement