Year: 2018
Type: preprint
Abstract: Zero-shot learning (ZSL) enables solving a task without the need to see its examples. In this paper, we propose two ZSL frameworks that learn to synthesize parameters for novel unseen classes. First, we propose to cast the problem of ZSL as learning manifold embeddings from graphs composed of object classes, leading to a flexible approach that synthesizes "classifiers" for the unseen classes. Then, we define an auxiliary task of synthesizing "exemplars" for the unseen classes to be used as an automatic denoising mechanism for any existing ZSL approaches or as an effective ZSL model by itself. On five visual recognition benchmark datasets, we demonstrate the superior performances of our proposed frameworks in various scenarios of both conventional and generalized ZSL. Finally, we provide valuable insights through a series of empirical analyses, among which are a comparison of semantic representations on the full ImageNet benchmark as well as a comparison of metrics used in generalized ZSL. Our code and data are publicly available at https://github.com/pujols/Zero-shot-learning-journal
Source: arXiv (Cornell University)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: RI: Medium: Collaborative Research: Learning to Summarize User-Generated Video, NRI-Small: Spacial Primitives for Enabling Situated Human-Robot Interaction, RI: Medium: Collaborative Research: Learning to Su, G5385673730, G7452299184, Collaborative Research: Socially Assistive Robots, G8257659198, RI: Medium: Collaborative Research: Semantically Discriminative: Guiding Mid-Level Representations for Visual Object Recognition with External Knowledge, RI: Medium: Collaborative Research: Learning to Su, EAGER: Leveraging Structure to Realize the Promise of Transfer Learning
OpenAlex ID: W2904897165