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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Both appearance cue and constraint cue are vital for human pose estimation.However, there is a tendency in most existing works to overfitting the formerand overlook the latter. In this paper, we propose Augmentation by InformationDropping (AID) to verify and tackle this dilemma. Alone with AID as aprerequisite for effectively exploiting its potential, we propose customizedtraining schedules, which are designed by analyzing the pattern of loss andperformance in training process from the perspective of information supplying.In experiments, as a model-agnostic approach, AID promotes variousstate-of-the-art methods in both bottom-up and top-down paradigms withdifferent input sizes, frameworks, backbones, training and testing sets. Onpopular COCO human pose estimation test set, AID consistently boosts theperformance of different configurations by around 0.6 AP in top-down paradigmand up to 1.5 AP in bottom-up paradigm. On more challenging CrowdPose dataset,the improvement is more than 1.5 AP. As AID successfully pushes the performanceboundary of human pose estimation problem by considerable margin and sets a newstate-of-the-art, we hope AID to be a regular configuration for training humanpose estimators. The source code will be publicly available for furtherresearch.

AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation