Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval
arXiv:1907.11832
Abstract
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
arXiv commentCVPR 2019
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Deep Learning Face Representation by Joint Identification-Verification
- Transductive Multi-view Zero-Shot Learning
- Smart Mining for Deep Metric Learning
- Discriminative Learning of Latent Features for Zero-Shot Recognition
- Zero-Shot Sketch-Image Hashing
- ALMN: Deep Embedding Learning with Geometrical Virtual Point Generating
- Deep Metric Learning with Angular Loss