Compressing Unknown Images With Product Quantizer for Efficient Zero-Shot Classification

For Zero-Shot Learning (ZSL), the Nearest Neighbor (NN) search is generally conducted for classification, which may cause unacceptable computational complexity for large-scale datasets. To compress zero-shot classes by the trained quantizer for efficient search, it tends to induce large quantization...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 5458 - 5467
Hauptverfasser:	Li, Jin, Lan, Xuguang, Liu, Yang, Wang, Le, Zheng, Nanning
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.06.2019
Schlagworte:	Big Data Categorization Codes Computational complexity Computer vision Image coding Large Scale Methods Nearest neighbor methods Quantization (signal) Recognition: Detection Retrieval Semantics Visualization Zero shot learning
ISSN:	1063-6919
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!