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

Semi-supervised object detection methods are widely used in autonomousdriving systems, where only a fraction of objects are labeled. To propagateinformation from the labeled objects to the unlabeled ones, pseudo-labels forunlabeled objects must be generated. Although pseudo-labels have proven toimprove the performance of semi-supervised object detection significantly, theapplications of image-based methods to video frames result in numerous miss orfalse detections using such generated pseudo-labels. In this paper, we proposea new approach, PseudoProp, to generate robust pseudo-labels by leveragingmotion continuity in video frames. Specifically, PseudoProp uses a novelbidirectional pseudo-label propagation approach to compensate for misdetection.A feature-based fusion technique is also used to suppress inference noise.Extensive experiments on the large-scale Cityscapes dataset demonstrate thatour method outperforms the state-of-the-art semi-supervised object detectionmethods by 7.4% on mAP75.

PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems