The promise of zero-shot learning for alcohol image detection: comparison with a task-specific deep learning algorithm

Background on zero-shot learning versus supervised learningIn essence, ZSL can perform image classification just like a supervised learning approach can. In contrast, using ZSL a model can classify images belonging to previously unseen classes with a reasonable accuracy. So, if either of these two phrases match the image then the image is predicted to be in “beer/cider bottle” class. We compared the performance metrics of ABIDLA2, ZSL using name-based phrases, ZSL using descriptive phrases across the three tasks. In addition, we also computed three separate confusion matrices to analyse the performance of each of ABIDLA2, ZSL using name-based phrases, ZSL using descriptive phrases vs annotators labels.