Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval
This work addresses zero-shot image retrieval, a domain-specific problem in computer vision, with incremental improvements over existing methods.
The paper tackles the problem of zero-shot image retrieval by proposing a Decoupled Metric Learning framework that addresses visual discriminative metric learning and prevents selective learning behavior, achieving state-of-the-art performance on popular benchmarks with significant improvements.
In zero-shot image retrieval (ZSIR) task, embedding learning becomes more attractive, however, many methods follow the traditional metric learning idea and omit the problems behind zero-shot settings. In this paper, we first emphasize the importance of learning visual discriminative metric and preventing the partial/selective learning behavior of learner in ZSIR, and then propose the Decoupled Metric Learning (DeML) framework to achieve these individually. Instead of coarsely optimizing an unified metric, we decouple it into multiple attention-specific parts so as to recurrently induce the discrimination and explicitly enhance the generalization. And they are mainly achieved by our object-attention module based on random walk graph propagation and the channel-attention module based on the adversary constraint, respectively. We demonstrate the necessity of addressing the vital problems in ZSIR on the popular benchmarks, outperforming the state-of-theart methods by a significant margin. Code is available at http://www.bhchen.cn