Author Archives: Fengyi Song

A survey on Zero-shot learning

Zero-shot learning (ZSL) has recently received extensive attention for its potential in achieving scalable object recognition with lower human labor cost relative to traditional supervised learning. However, zero-shot learning is a nontrivial problem, and its feasibility relies on satisfaction of  several important assumptions and conditions, where learning knowledge shareable between seen classes and unseen classes becomes the foundation. A plenty of works are proposed from different views with various formulations while obeying the foundation. We will review the literature of zero-shot learning comprehensively while putting emphasis on analyzing their motivations, assumptions, and exact mechanism for learning transferable knowledge that is helpful for connecting testing images and description of unseen classes. Finally, benchmarks for evaluating and comparing kinds of approaches are discussed mainly involving the datasets, protocols and evaluation measures. We hope this review may shed light on advanced solutions to zero-shot learning. Continue reading

Posted in Articles | Comments Off

A review of attribute relationship exploration and exploitation for improved object recognition

Recently, attribute-based representation has been extensively researched in the literature of computer vision due to its wide applications. While enjoying advantages of attributes such as clear semantic meaning and well generality in depicting differen… Continue reading

Posted in Articles | Comments Off