Two-stage Image Classification Supervised by a Single Teacher Single Student Model
This work addresses image classification by improving two-stage strategies, but it appears incremental as it builds on existing methods with a novel supervision approach.
The paper tackles the problem of two-stage image classification by proposing a novel two-stage representation method (TSR) that converts it into a Single-Teacher Single-Student (STSS) framework, where the first stage classifier supervises the second stage to generate a stronger classifier, and experiments on face and object databases show it outperforms multiple popular methods.
The two-stage strategy has been widely used in image classification. However, these methods barely take the classification criteria of the first stage into consideration in the second prediction stage. In this paper, we propose a novel two-stage representation method (TSR), and convert it to a Single-Teacher Single-Student (STSS) problem in our two-stage image classification framework. We seek the nearest neighbours of the test sample to choose candidate target classes. Meanwhile, the first stage classifier is formulated as the teacher, which holds the classification scores. The samples of the candidate classes are utilized to learn a student classifier based on L2-minimization in the second stage. The student will be supervised by the teacher classifier, which approves the student only if it obtains a higher score. In actuality, the proposed framework generates a stronger classifier by staging two weaker classifiers in a novel way. The experiments conducted on several face and object databases show that our proposed framework is effective and outperforms multiple popular classification methods.