Personalized Classifier for Food Image Recognition
This addresses the gap between lab-based food recognition and real-world personalization for users with limited and evolving data, though it is incremental in method.
The paper tackles the problem of food image recognition in dynamic real-world conditions where users continuously add samples and new classes, proposing a personalized classifier that adapts incrementally with limited data. Experimental results on a new dataset from a food-logging application show that the method significantly outperforms existing approaches.
Currently, food image recognition tasks are evaluated against fixed datasets. However, in real-world conditions, there are cases in which the number of samples in each class continues to increase and samples from novel classes appear. In particular, dynamic datasets in which each individual user creates samples and continues the updating process often have content that varies considerably between different users, and the number of samples per person is very limited. A single classifier common to all users cannot handle such dynamic data. Bridging the gap between the laboratory environment and the real world has not yet been accomplished on a large scale. Personalizing a classifier incrementally for each user is a promising way to do this. In this paper, we address the personalization problem, which involves adapting to the user's domain incrementally using a very limited number of samples. We propose a simple yet effective personalization framework which is a combination of the nearest class mean classifier and the 1-nearest neighbor classifier based on deep features. To conduct realistic experiments, we made use of a new dataset of daily food images collected by a food-logging application. Experimental results show that our proposed method significantly outperforms existing methods.