Zero-Shot Object Recognition System based on Topic Model
This addresses the problem of object recognition without labeled training data for researchers and practitioners in computer vision, offering an incremental improvement by removing annotation requirements.
The paper tackles zero-shot object recognition by proposing a novel strategy using topic models and hierarchical class concepts, eliminating the need for human annotation, and achieves comparable performance with state-of-the-art algorithms on four public datasets, with accuracies ranging from 49.65% to 67.09%.
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.