Learning adversarial semantic embeddings for zero-shot recognition in open worlds

• Main Authors: LI, Tianqi, PANG, Guansong, BAI, Xiao, ZHENG, Jin, ZHOU, Lei, NING, Xin
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Open-Set Recognition (OSR); Zero-Shot Learning (ZSL); Zero-Shot Open-Set Recognition (ZS-OSR); Artificial Intelligence and Robotics; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/8642; https://ink.library.smu.edu.sg/context/sis_research/article/9645/viewcontent/2307.03416.pdf
• Institution: Singapore Management University

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes for which neither samples (e.g., images) nor their side sema...