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

Learning-based edge detection has hereunto been strongly supervised withpixel-wise annotations which are tedious to obtain manually. We study theproblem of self-training edge detection, leveraging the untapped wealth oflarge-scale unlabeled image datasets. We design a self-supervised frameworkwith multi-layer regularization and self-teaching. In particular, we impose aconsistency regularization which enforces the outputs from each of the multiplelayers to be consistent for the input image and its perturbed counterpart. Weadopt L0-smoothing as the 'perturbation' to encourage edge prediction lying onsalient boundaries following the cluster assumption in self-supervisedlearning. Meanwhile, the network is trained with multi-layer supervision bypseudo labels which are initialized with Canny edges and then iterativelyrefined by the network as the training proceeds. The regularization andself-teaching together attain a good balance of precision and recall, leadingto a significant performance boost over supervised methods, with lightweightrefinement on the target dataset. Furthermore, our method demonstrates strongcross-dataset generality. For example, it attains 4.8% improvement for ODS and5.8% for OIS when tested on the unseen BIPED dataset, compared to thestate-of-the-art methods.

STEdge: Self-training Edge Detection with Multi-layer Teaching and Regularization