Optimized Autoencoder-Driven Semantic Feature Enhancement for Zero-Shot Image Classification
Advances in Technology Innovation · 22.06.2026 · 11 (3) · 304-319
DOI: 10.46604/aiti.2026.16231 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances in Technology Innovation, online erschienen am 22.06.2026. Verfasst von Shaista Khanam und 1 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Zero-shot learning (ZSL) identifies unseen categories using semantic knowledge transferred from seen classes. Its effectiveness depends on visual and semantic representations. This study aims to develop an optimized autoencoder-driven semantic feature extraction (OADSFE) framework based on a hybrid feature approach (HFA). The HFA combines deep spatial representations with multi-scale texture information to characterize visual data. Semantic features are derived using fastText, GloVe, BERT, and MPNet, which are evaluated independently. An autoencoder-based post-embedding optimization module compresses high-dimensional semantic embeddings into a compact latent space while preserving discriminative information, reducing memory usage and testing time. Evaluation on the AWA2, SUN, and CUB benchmark datasets demonstrates that the proposed framework achieves up to a 16.29% reduction in testing time and an 89.42% reduction in memory usage while maintaining classification performance across multiple embedding configurations. The proposed framework performs well across diverse datasets and semantic embedding strategies, indicating its suitability for scalable ZSL applications.
Zitieren
APA
Khanam, S., & Sonar, P. (2026). Optimized Autoencoder-Driven Semantic Feature Enhancement for Zero-Shot Image Classification. Advances in Technology Innovation, 11(3), 304-319. https://doi.org/10.46604/aiti.2026.16231
Vancouver
Khanam S, Sonar P. Optimized Autoencoder-Driven Semantic Feature Enhancement for Zero-Shot Image Classification. Advances in Technology Innovation. 2026;11(3):304-319. doi:10.46604/aiti.2026.16231
BibTeX
@article{Khanam2026,
author = {Khanam, Shaista and Sonar, Poonam},
title = {Optimized Autoencoder-Driven Semantic Feature Enhancement for Zero-Shot Image Classification},
journal = {Advances in Technology Innovation},
year = {2026},
volume = {11},
number = {3},
pages = {304--319},
doi = {10.46604/aiti.2026.16231}
}
EUVIMED