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

Humans have the remarkable ability to recognize and acquire novel visualconcepts in a zero-shot manner. Given a high-level, symbolic description of anovel concept in terms of previously learned visual concepts and theirrelations, humans can recognize novel concepts without seeing any examples.Moreover, they can acquire new concepts by parsing and communicating symbolicstructures using learned visual concepts and relations. Endowing thesecapabilities in machines is pivotal in improving their generalizationcapability at inference time. In this work, we introduce Zero-shot ConceptRecognition and Acquisition (ZeroC), a neuro-symbolic architecture that canrecognize and acquire novel concepts in a zero-shot way. ZeroC representsconcepts as graphs of constituent concept models (as nodes) and their relations(as edges). To allow inference time composition, we employ energy-based models(EBMs) to model concepts and relations. We design ZeroC architecture so that itallows a one-to-one mapping between a symbolic graph structure of a concept andits corresponding EBM, which for the first time, allows acquiring new concepts,communicating its graph structure, and applying it to classification anddetection tasks (even across domains) at inference time. We introducealgorithms for learning and inference with ZeroC. We evaluate ZeroC on achallenging grid-world dataset which is designed to probe zero-shot conceptrecognition and acquisition, and demonstrate its capability.

ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time