Zero-Shot Learning by Generating Pseudo Feature Representations

Abstract

Zero-shot learning (ZSL) is a challenging task aiming at recognizing novel classes without any training instances. In this paper we present a simple but high-performance ZSL approach by generating pseudo feature representations (GPFR). Given the dataset of seen classes and side information of unseen classes (e.g. attributes), we synthesize feature-level pseudo representations for novel concepts, which allows us access to the formulation of unseen class predictor. Firstly we design a Joint Attribute Feature Extractor (JAFE) to acquire understandings about attributes, then construct a cognitive repository of attributes filtered by confidence margins, and finally generate pseudo feature representations using a probability based sampling strategy to facilitate subsequent training process of class predictor. We demonstrate the effectiveness in ZSL settings and the extensibility in supervised recognition scenario of our method on a synthetic colored MNIST dataset (C-MNIST). For several popular ZSL benchmark datasets, our approach also shows compelling results on zero-shot recognition task, especially leading to tremendous improvement to state-of-the-art mAP on zero-shot retrieval task.

9 pages

References in corpus (8)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• TensorFlow: A system for large-scale machine learning
• Label-Embedding for Image Classification
• Transductive Multi-view Zero-Shot Learning
• Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions
• Zero-Shot Learning via Semantic Similarity Embedding
• Latent Embeddings for Zero-shot Classification
• Online but Accurate Inference for Latent Variable Models with Local Gibbs Sampling

Cited by in corpus (6)

• Small Sample Learning in Big Data Era
• Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learning
• Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing
• Additive Adversarial Learning for Unbiased Authentication
• Zero-Shot Learning via Latent Space Encoding
• Domain Agnostic Learning for Unbiased Authentication