Zero-Shot Learning with Generative Latent Prototype Model
arXiv:1705.09474
Abstract
Zero-shot learning, which studies the problem of object classification for categories for which we have no training examples, is gaining increasing attention from community. Most existing ZSL methods exploit deterministic transfer learning via an in-between semantic embedding space. In this paper, we try to attack this problem from a generative probabilistic modelling perspective. We assume for any category, the observed representation, e.g. images or texts, is developed from a unique prototype in a latent space, in which the semantic relationship among prototypes is encoded via linear reconstruction. Taking advantage of this assumption, virtual instances of unseen classes can be generated from the corresponding prototype, giving rise to a novel ZSL model which can alleviate the domain shift problem existing in the way of direct transfer learning. Extensive experiments on three benchmark datasets show our proposed model can achieve state-of-the-art results.
This work was completed in Oct, 2016
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distributed Representations of Words and Phrases and their Compositionality
- Going Deeper with Convolutions
- Zero-Shot Learning by Convex Combination of Semantic Embeddings
- Zero Shot Recognition with Unreliable Attributes
- Zero-Shot Learning via Semantic Similarity Embedding
- Learning Attributes Equals Multi-Source Domain Generalization
- Multi-Cue Zero-Shot Learning with Strong Supervision
Cited by in corpus (4)
- Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly
- Zero-Shot Learning via Class-Conditioned Deep Generative Models
- An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning
- Discriminative Embedding Autoencoder with a Regressor Feedback for Zero-Shot Learning