`Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning
This addresses the problem of novel category recognition in GZSL for computer vision researchers, offering a more practical approach with localized proposals, though it is incremental as it builds on existing base models.
The paper tackles the oversimplification in Generalized Zero-Shot Learning (GZSL) by proposing a Part Prototype Network (PPN) that uses region-specific attribute attention from a Vision-Language detector, achieving promising results on CUB, SUN, and AWA2 datasets.
Current approaches in Generalized Zero-Shot Learning (GZSL) are built upon base models which consider only a single class attribute vector representation over the entire image. This is an oversimplification of the process of novel category recognition, where different regions of the image may have properties from different seen classes and thus have different predominant attributes. With this in mind, we take a fundamentally different approach: a pre-trained Vision-Language detector (VINVL) sensitive to attribute information is employed to efficiently obtain region features. A learned function maps the region features to region-specific attribute attention used to construct class part prototypes. We conduct experiments on a popular GZSL benchmark consisting of the CUB, SUN, and AWA2 datasets where our proposed Part Prototype Network (PPN) achieves promising results when compared with other popular base models. Corresponding ablation studies and analysis show that our approach is highly practical and has a distinct advantage over global attribute attention when localized proposals are available.