Zero-Shot Object Recognition System based on Topic Model

TL;DR

This paper introduces a zero-shot object recognition system leveraging topic models and hierarchical class concepts, eliminating the need for manual attribute annotation and achieving competitive results on multiple datasets.

Contribution

The paper presents a novel zero-shot learning approach that removes the manual annotation step by using topic models and class hierarchies, improving efficiency.

Findings

Achieved 67.09% accuracy on PubFig dataset.

Performed comparably on Cifar-100 with 54.85%.

Outperformed some existing methods on multiple datasets.

Abstract

Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier learning stage, a task also known as zero-shot learning. We propose a novel zero-shot learning strategy that utilizes the topic model and hierarchical class concept. Our proposed method advanced where cumbersome human annotation stage (i.e. attribute-based classification) is eliminated. We achieve comparable performance with state-of-the-art algorithms in four public datasets: PubFig (67.09%), Cifar-100 (54.85%), Caltech-256 (52.14%), and Animals with Attributes (49.65%) when unseen classes exist in the classification task.