A deep hashing method based on attention module for image retrieval

Long, Jun; Wei, Xiangxiang; Qi, Qianqian; Wang, Ye

doi:10.1109/icicta51737.2020.00066

Cited by 2 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jin et al [37] put forward deep ordinal hashing (DOH), which uses effective spatial attention to emphasize relevant information in local space. Long et al [26] combined an attention mechanism with a deep hashing retrieval algorithm; the spatial and channel attention models are embedded in the CNN to improve the ability of image feature expression. Yang et al [38] presented a deep hashing algorithm with parameter-free attention to improve extraction ability of image semantic, where an energy function is used to assign attention weight for feature maps.…”

Section: Supervised Hashingmentioning

confidence: 99%

See 1 more Smart Citation

Deep Cross-Dimensional Attention Hashing for Image Retrieval

Chao

Li²

2022

Information

View full text Add to dashboard Cite

Nowadays, people’s lives are filled with a huge amount of picture information, and image retrieval tasks are widely needed. Deep hashing methods are extensively used to manage such demands due to their retrieval rate and memory consumption. The problem with conventional deep hashing image retrieval techniques, however, is that high dimensional semantic content in the image cannot be effectively articulated due to insufficient and unbalanced feature extraction. This paper offers the deep cross-dimensional attention hashing (DCDAH) method considering the flaws in feature extraction, and the important points of this paper are as follows. This paper proposes a cross-dimensional attention (CDA) module embedded in ResNet18; the module can capture the cross-dimension interaction of feature maps to calculate the attention weight effectively because of its special branch. For a feature map acquired by a convolutional neural network (CNN), each branch takes different rotation measurements and residual transformations to process it. To prevent the DCDAH model from becoming too complex, the CDA module is designed to have the characteristics of low computational overhead. This paper introduces a scheme to reduce the dimension of tensors, which can reduce computation and retain abundant representation. For a dimension of a feature map, the Maxpool and Avgpool are performed, respectively, and the two results are connected. The DCDAH method significantly enhances image retrieval performance, according to studies on the CIFAR10 and NUS-WIDE data sets.

show abstract

Section: Supervised Hashingmentioning

confidence: 99%

“…The accuracy of the hash code is decreased as a result of the inevitable quantization error that occurs during the binary mapping process while utilizing the hash function. In order to compensate for the defects in feature extraction, many scholars introduce attention mechanisms [2,22,26,27].…”

Section: Introductionmentioning

confidence: 99%