A Cross-Modal Alignment for Zero-Shot Image Classification

Different from major classification methods based on large amounts of annotation data, we introduce a cross-modal alignment for zero-shot image classification.The key is utilizing the query of text attribute learned from the seen classes to guide local feature responses in unseen classes. First, an...

Cijeli opis

Bibliografski detalji

Glavni autori:	Lu Wu, Chenyu Wu, Han Guo, Zhihao Zhao
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2023-01-01
Serija:	IEEE Access
Teme:	Cross-modal alignment zero-shot image classification text attribute query cosine similarity
Online pristup:	https://ieeexplore.ieee.org/document/10018960/
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!