How to Transfer? Zero-Shot Object Recognition via Hierarchical Transfer of Semantic Attributes

TL;DR

This paper introduces a hierarchical transfer model for zero-shot object recognition that leverages category structure and attribute variations, significantly improving transfer accuracy across multiple datasets.

Contribution

It proposes a hierarchical attribute transfer approach that captures intra-attribute variations and selectively shares attributes with unseen classes, advancing zero-shot recognition.

Findings

Significant improvement over state-of-the-art methods

Effective modeling of attribute variations within categories

Successful application on three public datasets

Abstract

Attribute based knowledge transfer has proven very successful in visual object analysis and learning previously unseen 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 appropriate 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 experiments demonstrate the effectiveness of our model with significant improvement over state-of-the-art.