Discriminative Learning of Latent Features for Zero-Shot Recognition

Abstract

Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the proper mapping matrices aligning the visual and semantic space, whilst the importance to learn discriminative representations for ZSL is ignored. In this work, we retrospect existing methods and demonstrate the necessity to learn discriminative representations for both visual and semantic instances of ZSL. We propose an end-to-end network that is capable of 1) automatically discovering discriminative regions by a zoom network; and 2) learning discriminative semantic representations in an augmented space introduced for both user-defined and latent attributes. Our proposed method is tested extensively on two challenging ZSL datasets, and the experiment results show that the proposed method significantly outperforms state-of-the-art methods.

arXiv commentCVPR 2018 (Oral)

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Transductive Multi-view Zero-Shot Learning
• Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly
• Local Similarity-Aware Deep Feature Embedding
• An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
• Semantically Consistent Regularization for Zero-Shot Recognition
• Zero-Shot Recognition using Dual Visual-Semantic Mapping Paths

Cited by in corpus (6)

• Transductive Zero-Shot Learning with Visual Structure Constraint
• Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval
• Bi-Adversarial Auto-Encoder for Zero-Shot Learning
• Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning
• Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification
• Beyond Attributes: Adversarial Erasing Embedding Network for Zero-shot Learning