Multimodal few-shot classification without attribute embedding

• Main Authors: Chang, Jun Qing, Rajan, Deepu, Vun, Nicholas
• 其他作者: School of Computer Science and Engineering
• 格式: Article
• 語言: English
• 出版: 2024
• 主題: Computer and Information Science; Multimodal learning; Few-shot classifcation
• 在線閱讀: https://hdl.handle.net/10356/175469
• 機構: Nanyang Technological University

Multimodal few-shot learning aims to exploit complementary information inherent in multiple modalities for vision tasks in low data scenarios. Most of the current research focuses on a suitable embedding space for the various modalities. While solutions based on embedding provide state-of-the-art re...