Recent work in visual recognition have addressed attribute-based classification. However, semantic attributes that are designed and labeled by humans generally contain some noise, and have weak learnability for classifiers and discrimination between categories. As a fine supplement to semantic attribute, data-driven attribute learned from training data suffers from the ineffectiveness in novel category classification with no or few samples. In this paper, we introduce the Discriminative Latent Attribute (DLA) as a mid-level representation, which has connection with both visual low-level feature and semantic attribute through matrix factorization. Furthermore, we propose a novel unified formulation to efficiently train category-DLA matrix and attribute classifiers together, which makes DLA more learnable and more discriminative between categories. Our experiments show the effectiveness and robustness of our approach which outperforms the state-of-the-art approach in zero-shot learning task.
Weitere Kapitel dieses Buchs durch Wischen aufrufen
Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten
Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:
- Robust Attribute-Based Visual Recognition Using Discriminative Latent Representation
- Springer International Publishing