Abstract: Deep metric learning has shown significantly increasing values in a wide range of domains, such as image retrieval, face recognition, zero-shot learning, to name a few. When evaluating the methods for deep metric learning, top-k precision is commonly used as a key metric, since few users bother to scroll down to lower-ranked items. Despite being widely studied, how to directly optimize top-k precision is still an open problem. In this paper, we propose a new method on how to optimize top-k precision in a rank-sensitive manner. Given the cutoff value k, our key idea is to impose different weights to further differentiate misplaced images sampled according to the top-k precision. To validate the effectiveness of the proposed method, we conduct a series of experiments on three widely used benchmark datasets. The experimental results demonstrate that: (1) Our proposed method outperforms the baseline methods on two datasets, which shows the potential value of rank-sensitive optimization of top-k precision for deep metric learning. (2) The factors, such as batch size and cutoff value k, significantly affect the performance of approaches that rely on optimising top-k precision for deep metric learning. Careful examinations of these factors are highly recommended.
Loading