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

Discovering novel concepts from unlabelled data and in a continuous manner isan important desideratum of lifelong learners. In the literature such problemshave been partially addressed under very restricted settings, where eitheraccess to labelled data is provided for discovering novel concepts (e.g., NCD)or learning occurs for a limited number of incremental steps (e.g.,class-iNCD). In this work we challenge the status quo and propose a morechallenging and practical learning paradigm called MSc-iNCD, where learningoccurs continuously and unsupervisedly, while exploiting the rich priors fromlarge-scale pre-trained models. To this end, we propose simple baselines thatare not only resilient under longer learning scenarios, but are surprisinglystrong when compared with sophisticated state-of-the-art methods. We conductextensive empirical evaluation on a multitude of benchmarks and show theeffectiveness of our proposed baselines, which significantly raises the bar.

Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery