Semantic Scholar Open Access 2017 311 sitasi

Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks

Long Chen Hanwang Zhang Jun Xiao W. Liu Shih-Fu Chang

Lihat Sumber DOI

Abstrak

We propose a novel framework called Semantics-Preserving Adversarial Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their classes are both unseen during training. SP-AEN aims to tackle the inherent problem - semantic loss - in the prevailing family of embedding-based ZSL, where some semantics would be discarded during training if they are non-discriminative for training classes, but could become critical for recognizing test classes. Specifically, SP-AEN prevents the semantic loss by introducing an independent visual-to-semantic space embedder which disentangles the semantic space into two subspaces for the two arguably conflicting objectives: classification and reconstruction. Through adversarial learning of the two subspaces, SP-AEN can transfer the semantics from the reconstructive subspace to the discriminative one, accomplishing the improved zero-shot recognition of unseen classes. Comparing

Topik & Kata Kunci

Computer Science

Penulis (5)

Long Chen

Hanwang Zhang

Jun Xiao

W. Liu

Shih-Fu Chang

Format Sitasi

APA MLA BibTeX

Chen, L., Zhang, H., Xiao, J., Liu, W., Chang, S. (2017). Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks. https://doi.org/10.1109/CVPR.2018.00115

Akses Cepat

Lihat di Sumber doi.org/10.1109/CVPR.2018.00115

Informasi Jurnal

Tahun Terbit: 2017
Bahasa: en
Total Sitasi: 311×
Sumber Database: Semantic Scholar
DOI: 10.1109/CVPR.2018.00115
Akses: Open Access ✓