Learning Clusterable Visual Features for Zero-Shot Recognition

Abstract

In zero-shot learning (ZSL), conditional generators have been widely used to generate additional training features. These features can then be used to train the classifiers for testing data. However, some testing data are considered "hard" as they lie close to the decision boundaries and are prone to misclassification, leading to performance degradation for ZSL. In this paper, we propose to learn clusterable features for ZSL problems. Using a Conditional Variational Autoencoder (CVAE) as the feature generator, we project the original features to a new feature space supervised by an auxiliary classification loss. To further increase clusterability, we fine-tune the features using Gaussian similarity loss. The clusterable visual features are not only more suitable for CVAE reconstruction but are also more separable which improves classification accuracy. Moreover, we introduce Gaussian noise to enlarge the intra-class variance of the generated features, which helps to improve the classifier's robustness. Our experiments on SUN,CUB, and AWA2 datasets show consistent improvement over previous state-of-the-art ZSL results by a large margin. In addition to its effectiveness on zero-shot classification, experiments show that our method to increase feature clusterability benefits few-shot learning algorithms as well.

References in corpus (16)

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Prototypical Networks for Few-shot Learning
• Zero-Shot Learning Through Cross-Modal Transfer
• Delta-encoder: an effective sample synthesis method for few-shot object recognition
• CosFace: Large Margin Cosine Loss for Deep Face Recognition
• A Closer Look at Few-shot Classification
• Semantic Autoencoder for Zero-Shot Learning
• Leveraging the Invariant Side of Generative Zero-Shot Learning
• Latent Embeddings for Zero-shot Classification
• Synthesized Classifiers for Zero-Shot Learning
• Zero-shot Learning via Simultaneous Generating and Learning
• Online but Accurate Inference for Latent Variable Models with Local Gibbs Sampling
• Multi-modal Cycle-consistent Generalized Zero-Shot Learning
• Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition
• Learning Joint Feature Adaptation for Zero-Shot Recognition