Noise-resistant Deep Metric Learning with Ranking-based Instance Selection
This addresses the issue of noisy labels in deep metric learning, which is a domain-specific problem for researchers and practitioners in computer vision, and represents an incremental advance over prior work.
The paper tackles the problem of noisy labels in deep metric learning by proposing PRISM, a noise-resistant training technique that uses ranking-based instance selection with a memory bank, achieving up to 6.06% improvement in Precision@1 compared to existing methods.
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains open. In this paper, we propose a noise-resistant training technique for DML, which we name Probabilistic Ranking-based Instance Selection with Memory (PRISM). PRISM identifies noisy data in a minibatch using average similarity against image features extracted by several previous versions of the neural network. These features are stored in and retrieved from a memory bank. To alleviate the high computational cost brought by the memory bank, we introduce an acceleration method that replaces individual data points with the class centers. In extensive comparisons with 12 existing approaches under both synthetic and real-world label noise, PRISM demonstrates superior performance of up to 6.06% in Precision@1.