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

Although existing semi-supervised learning models achieve remarkable successin learning with unannotated in-distribution data, they mostly fail to learn onunlabeled data sampled from novel semantic classes due to their closed-setassumption. In this work, we target a pragmatic but under-explored GeneralizedNovel Category Discovery (GNCD) setting. The GNCD setting aims to categorizeunlabeled training data coming from known and novel classes by leveraging theinformation of partially labeled known classes. We propose a two-stageContrastive Affinity Learning method with auxiliary visual Prompts, dubbedPromptCAL, to address this challenging problem. Our approach discovers reliablepairwise sample affinities to learn better semantic clustering of both knownand novel classes for the class token and visual prompts. First, we propose adiscriminative prompt regularization loss to reinforce semanticdiscriminativeness of prompt-adapted pre-trained vision transformer for refinedaffinity relationships.Besides, we propose contrastive affinity learning tocalibrate semantic representations based on our iterative semi-supervisedaffinity graph generation method for semantically-enhanced supervision.Extensive experimental evaluation demonstrates that our PromptCAL method ismore effective in discovering novel classes even with limited annotations andsurpasses the current state-of-the-art on generic and fine-grained benchmarks(e.g., with nearly 11% gain on CUB-200, and 9% on ImageNet-100) on overallaccuracy. Our code is available at https://github.com/sheng-eatamath/PromptCAL.

PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery