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

This paper proposes a novel paradigm for the unsupervised learning of objectlandmark detectors. Contrary to existing methods that build on auxiliary taskssuch as image generation or equivariance, we propose a self-training approachwhere, departing from generic keypoints, a landmark detector and descriptor istrained to improve itself, tuning the keypoints into distinctive landmarks. Tothis end, we propose an iterative algorithm that alternates between producingnew pseudo-labels through feature clustering and learning distinctive featuresfor each pseudo-class through contrastive learning. With a shared backbone forthe landmark detector and descriptor, the keypoint locations progressivelyconverge to stable landmarks, filtering those less stable. Compared to previousworks, our approach can learn points that are more flexible in terms ofcapturing large viewpoint changes. We validate our method on a variety ofdifficult datasets, including LS3D, BBCPose, Human3.6M and PennAction,achieving new state of the art results.

From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery