Portal de Periódicos da CAPES

Attribute-Based Synthetic Network (ABS-Net): Learning more from pseudo feature representations

2018; Elsevier BV; Volume: 80; Linguagem: Inglês

10.1016/j.patcog.2018.03.006

1873-5142

Jiang Lu, Jin Li, Ziang Yan, Fenghua Mei, Changshui Zhang,

Advanced Graph Neural Networks

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.