当前位置: X-MOL 学术IEEE Signal Process. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Unsupervised Discriminative Deep Hashing With Locality and Globality Preservation
IEEE Signal Processing Letters ( IF 3.2 ) Pub Date : 2021-02-24 , DOI: 10.1109/lsp.2021.3059526
Zhuyi Ni , Zexuan Ji , Long Lan , Yun-Hao Yuan , Xiaobo Shen

Deep hashing has greatly improved retrieval performance with the powerful learning capability of deep neural network. However, deep unsupervised hashing can hardly achieve impressive performance due to the lack of the semantic supervision. This letter proposes Unsupervised Discriminative Deep Hashing (UD 2 H) to fulfill this gap. UD 2 H is formulated to jointly perform hash code learning and clustering, and trained in an asymmetric manner to improve the efficiency. The cluster labels supervise the training of deep model to enable hash code discriminative. Based on the outputs of the deep model, UD 2 H adaptively constructs a similarity graph that considers the local and global structures. Experiments on three benchmark datasets show that the proposed UD2H outperforms the state-of-the-art unsupervised deep hashing methods.

中文翻译:


具有局部性和全局性保留的无监督区分深度哈希



深度哈希借助深度神经网络强大的学习能力,极大地提高了检索性能。然而,由于缺乏语义监督,深度无监督哈希很难取得令人印象深刻的性能。这封信提出了无监督判别深度哈希(UD 2 H)来填补这一空白。 UD 2 H被制定为联合执行哈希码学习和聚类,并以非对称方式训练以提高效率。集群标签监督深度模型的训练,以实现哈希码区分。基于深度模型的输出,UD 2 H 自适应地构建考虑局部和全局结构的相似图。对三个基准数据集的实验表明,所提出的 UD2H 优于最先进的无监督深度哈希方法。
更新日期:2021-02-24
down
wechat
bug