How to Transfer? Zero-Shot Object Recognition via Hierarchical Transfer of Semantic Attributes
Ziad Al-Halah, Rainer Stiefelhagen · 2015
Attribute based knowledge transfer has proven very suc-cessful in visual object analysis and learning previously un-seen classes. However, the common approach learns and transfers attributes without taking into consideration the embedded structure between the categories in the source set. Such information provides important cues on the intra-attribute variations. We propose to capture these variations in a hierarchical model that expands the knowledge source with additional abstraction levels of attributes. We also provide a novel transfer approach that can choose the ap-propriate attributes to be shared with an unseen class. We evaluate our approach on three public datasets: aPascal, Animals with Attributes and CUB-200-2011 Birds. The ex-periments demonstrate the effectiveness of our model with significant improvement over state-of-the-art. 1.