Transductive Unbiased Embedding for Zero-Shot Learning

Abstract

Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in the generalized ZSL settings. In this paper, we propose a straightforward yet effective method named Quasi-Fully Supervised Learning (QFSL) to alleviate the bias problem. Our method follows the way of transductive learning, which assumes that both the labeled source images and unlabeled target images are available for training. In the semantic embedding space, the labeled source images are mapped to several fixed points specified by the source categories, and the unlabeled target images are forced to be mapped to other points specified by the target categories. Experiments conducted on AwA2, CUB and SUN datasets demonstrate that our method outperforms existing state-of-the-art approaches by a huge margin of 9.3~24.5% following generalized ZSL settings, and by a large margin of 0.2~16.2% following conventional ZSL settings.

Accepted to CVPR2018

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Estimation of Word Representations in Vector Space
• Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly
• Zero-Shot Learning via Semantic Similarity Embedding
• An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
• Ridge Regression, Hubness, and Zero-Shot Learning
• Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learning
• Semi-supervised Vocabulary-informed Learning
• Semantically Consistent Regularization for Zero-Shot Recognition
• Visually Aligned Word Embeddings for Improving Zero-shot Learning

Cited by in corpus (5)

• Transductive Zero-Shot Learning with Visual Structure Constraint
• Zero-Shot Semantic Segmentation
• Visual Space Optimization for Zero-shot Learning
• Transfer feature generating networks with semantic classes structure for zero-shot learning
• Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning