Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning

Abstract

Collecting training images for all visual categories is not only expensive but also impractical. Zero-shot learning (ZSL), especially using attributes, offers a pragmatic solution to this problem. However, at test time most attribute-based methods require a full description of attribute associations for each unseen class. Providing these associations is time consuming and often requires domain specific knowledge. In this work, we aim to carry out attribute-based zero-shot classification in an unsupervised manner. We propose an approach to learn relations that couples class embeddings with their corresponding attributes. Given only the name of an unseen class, the learned relationship model is used to automatically predict the class-attribute associations. Furthermore, our model facilitates transferring attributes across data sets without additional effort. Integrating knowledge from multiple sources results in a significant additional improvement in performance. We evaluate on two public data sets: Animals with Attributes and aPascal/aYahoo. Our approach outperforms state-of-the-art methods in both predicting class-attribute associations and unsupervised ZSL by a large margin.

Published as a conference paper at CVPR 2016

References in corpus (3)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Going Deeper with Convolutions
• Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions

Cited by in corpus (13)

• Zero-Shot Learning posed as a Missing Data Problem
• Semantically Consistent Regularization for Zero-Shot Recognition
• Learning Joint Feature Adaptation for Zero-Shot Recognition
• Zero-Shot Sketch-Image Hashing
• Transductive Zero-Shot Learning with a Self-training dictionary approach
• Large-Scale Attribute-Object Compositions
• Zero-Shot Learning via Category-Specific Visual-Semantic Mapping
• Global Semantic Consistency for Zero-Shot Learning
• Complementary Attributes: A New Clue to Zero-Shot Learning
• End-to-end Generative Zero-shot Learning via Few-shot Learning
• Automatic Discovery, Association Estimation and Learning of Semantic Attributes for a Thousand Categories
• Towards Robust Pattern Recognition: A Review
• Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection