当前位置: X-MOL 学术Pattern Recogn. 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.)
Attention-aware invertible hashing network with skip connections
Pattern Recognition Letters ( IF 5.1 ) Pub Date : 2020-09-03 , DOI: 10.1016/j.patrec.2020.09.002
Shanshan Li , Qiang Cai , Zhuangzi Li , Haisheng Li , Naiguang Zhang , Xiaoyu Zhang

In recent years, Convolutional Neural Networks (CNNs) have shown promising performance on image hashing retrieval. However, due to the information-discarded nature of CNN, some meaningful information can not be further extracted into a deep level and embedded into hash codes. To solve the problem, this study attempts to design an invertible CNN feature extractor to fully maintain input information meanwhile having well generalization ability. Specifically, we propose a novel Attention-Aware Invertible Hashing Network with Skip Connection (AIHN-SC) for image retrieval. Represented by an invertible feature, the hash code can be learned and generated from image characteristics preserving all input information. For achieving favourable generalization ability in our invertible architecture, we present a novel spatial attention mechanism to highlight regions involving semantic information. In addition, we introduce two kinds of skip connection, i.e. hierarchical and residual connections, which aim to provide richer knowledges for hash code learning and ease our training process. Extensive experiments on benchmark datasets demonstrate the effectiveness of our proposed AIHN-SC and show the significant performance in image retrieval against the state-of-the-arts.



中文翻译:

具有跳过连接的注意感知的可逆哈希网络

近年来,卷积神经网络(CNN)在图像哈希检索上显示出令人鼓舞的性能。但是,由于CNN的信息丢弃特性,一些有意义的信息无法进一步提取到更深的层次中并嵌入到哈希码中。为了解决该问题,本研究试图设计一种可逆的CNN特征提取器,以在保持良好的泛化能力的同时,充分维护输入信息。具体来说,我们提出了一种新颖的具有跳过连接的注意感知可逆哈希网络(AIHN-SC),用于图像检索。以可逆特征表示,可以从保留所有输入信息的图像特征中学习并生成哈希码。为了在我们的可逆架构中实现良好的泛化能力,我们提出了一种新颖的空间注意机制,以突出显示涉及语义信息的区域。另外,我们介绍了两种跳过连接,即分层连接和残留连接,旨在为哈希码学习提供更丰富的知识并简化我们的训练过程。在基准数据集上进行的大量实验证明了我们提出的AIHN-SC的有效性,并显示了在针对最新技术的图像检索中的显着性能。

更新日期:2020-09-10
down
wechat
bug