Cascading Hierarchical Networks with Multi-task Balanced Loss for Fine-grained hashing
This work addresses the problem of efficient and accurate retrieval from large-scale fine-grained images for applications like image search, with incremental improvements in hashing techniques.
The paper tackles the challenge of retrieving fine-grained images with low inter-class and high intra-class variance by proposing a cascaded hierarchical network with attention-guided data augmentation and a multi-task balanced loss, achieving improved retrieval accuracy over state-of-the-art hashing methods on common datasets.
With the explosive growth in the number of fine-grained images in the Internet era, it has become a challenging problem to perform fast and efficient retrieval from large-scale fine-grained images. Among the many retrieval methods, hashing methods are widely used due to their high efficiency and small storage space occupation. Fine-grained hashing is more challenging than traditional hashing problems due to the difficulties such as low inter-class variances and high intra-class variances caused by the characteristics of fine-grained images. To improve the retrieval accuracy of fine-grained hashing, we propose a cascaded network to learn compact and highly semantic hash codes, and introduce an attention-guided data augmentation method. We refer to this network as a cascaded hierarchical data augmentation network. We also propose a novel approach to coordinately balance the loss of multi-task learning. We do extensive experiments on some common fine-grained visual classification datasets. The experimental results demonstrate that our proposed method outperforms several state-of-art hashing methods and can effectively improve the accuracy of fine-grained retrieval. The source code is publicly available: https://github.com/kaiba007/FG-CNET.