Classifier and Exemplar Synthesis for Zero-Shot Learning
arXiv:1812.06423
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
arXiv commentExtended version of arXiv:1603.00550 (CVPR 2016) and arXiv:1605.08151 (ICCV 2017); Accepted for publication in International Journal of Computer Vision (IJCV)
References in corpus (15)
- Efficient Estimation of Word Representations in Vector Space
- Distributed Representations of Words and Phrases and their Compositionality
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Generative Adversarial Text to Image Synthesis
- Zero-Shot Learning by Convex Combination of Semantic Embeddings
- Transductive Multi-view Zero-Shot Learning
- Zero Shot Recognition with Unreliable Attributes
- Learning Deep Representations of Fine-grained Visual Descriptions
- The Devil is in the Tails: Fine-grained Classification in the Wild
- Zero-Shot Learning -- The Good, the Bad and the Ugly
- An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
- Latent Embeddings for Zero-shot Classification
- Synthesized Classifiers for Zero-Shot Learning
- From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis
- Learning Attributes Equals Multi-Source Domain Generalization