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

Addressing Out-Of-Distribution (OOD) Segmentation and Zero-Shot SemanticSegmentation (ZS3) is challenging, necessitating segmenting unseen classes.Existing strategies adapt the class-agnostic Mask2Former (CA-M2F) tailored tospecific tasks. However, these methods cater to singular tasks, demand trainingfrom scratch, and we demonstrate certain deficiencies in CA-M2F, which affectperformance. We propose the Class-Agnostic Structure-Constrained Learning(CSL), a plug-in framework that can integrate with existing methods, therebyembedding structural constraints and achieving performance gain, including theunseen, specifically OOD, ZS3, and domain adaptation (DA) tasks. There are twoschemes for CSL to integrate with existing methods (1) by distilling knowledgefrom a base teacher network, enforcing constraints across training andinference phrases, or (2) by leveraging established models to obtain per-pixeldistributions without retraining, appending constraints during the inferencephase. We propose soft assignment and mask split methodologies that enhance OODobject segmentation. Empirical evaluations demonstrate CSL's prowess inboosting the performance of existing algorithms spanning OOD segmentation, ZS3,and DA segmentation, consistently transcending the state-of-art across allthree tasks.

CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen