Domain-Invariant Projection Learning for Zero-Shot Recognition

Abstract

Zero-shot learning (ZSL) aims to recognize unseen object classes without any training samples, which can be regarded as a form of transfer learning from seen classes to unseen ones. This is made possible by learning a projection between a feature space and a semantic space (e.g. attribute space). Key to ZSL is thus to learn a projection function that is robust against the often large domain gap between the seen and unseen classes. In this paper, we propose a novel ZSL model termed domain-invariant projection learning (DIPL). Our model has two novel components: (1) A domain-invariant feature self-reconstruction task is introduced to the seen/unseen class data, resulting in a simple linear formulation that casts ZSL into a min-min optimization problem. Solving the problem is non-trivial, and a novel iterative algorithm is formulated as the solver, with rigorous theoretic algorithm analysis provided. (2) To further align the two domains via the learned projection, shared semantic structure among seen and unseen classes is explored via forming superclasses in the semantic space. Extensive experiments show that our model outperforms the state-of-the-art alternatives by significant margins.

arXiv commentAccepted to NIPS 2018

Cited by in corpus (16)

• Learning Robust Global Representations by Penalizing Local Predictive Power
• Polarity Loss for Zero-shot Object Detection
• Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
• Meta-Learning across Meta-Tasks for Few-Shot Learning
• Adaptive Confidence Smoothing for Generalized Zero-Shot Learning
• Visual Space Optimization for Zero-shot Learning
• Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
• From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition
• Hierarchical Prototype Learning for Zero-Shot Recognition
• ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries
• Joint Concept Matching based Learning for Zero-Shot Recognition
• Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts
• Convolutional Prototype Learning for Zero-Shot Recognition
• Transductive Zero-Shot Learning using Cross-Modal CycleGAN
• Transductive Zero-Shot Learning by Decoupled Feature Generation
• Zero-Shot Learning with Sparse Attribute Propagation