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 learning aims to boost the accuracy of a model by exploringunlabeled images. The state-of-the-art methods are consistency-based whichlearn about unlabeled images by encouraging the model to give consistentpredictions for images under different augmentations. However, when applied topose estimation, the methods degenerate and predict every pixel in unlabeledimages as background. This is because contradictory predictions are graduallypushed to the background class due to highly imbalanced class distribution. Butthis is not an issue in supervised learning because it has accurate labels.This inspires us to stabilize the training by obtaining reliable pseudo labels.Specifically, we learn two networks to mutually teach each other. Inparticular, for each image, we compose an easy-hard pair by applying differentaugmentations and feed them to both networks. The more reliable predictions oneasy images in each network are used to teach the other network to learn aboutthe corresponding hard images. The approach successfully avoids degenerationand achieves promising results on public datasets. The source code andpretrained models have been released athttps://github.com/xierc/Semi_Human_Pose.

An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation