.png){kind=icon}
Return
Image Retrieval Using Multilayer Feature Aggregation Histogram
.png){kind=icon}
PRE
AI
DOI：10.1007/s12559-024-10334-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Aggregating the diverse features into a compact representation is a hot issue in image retrieval. However, aggregating the differential feature of multilayer into a discriminative representation remains challenging. Inspired by the value-guided neural mechanisms, a novel representation method, namely, the multilayer feature aggregation histogram was proposed to image retrieval. It can aggregate multilayer features, such as low-, mid-, and high-layer features, into a discriminative yet compact representation via simulating the neural mechanisms that mediate the ability to make value-guided decisions. The highlights of the proposed method have the following: (1) A detail-attentive map was proposed to represent the aggregation of low- and mid-layer features. It can be well used to evaluate the distinguishable detail feature. (2) A simple yet straightforward aggregation method is proposed to re-evaluate the distinguishable high-layer feature. It can provide aggregated features including detail, object, and semantic by using semantic-attentive map. (3) A novel whitening method, namely difference whitening, is introduced to reduce dimensionality. It did not need to seek a training dataset of semantical similarity and can provide a compact yet discriminative representation. Experiments on the popular benchmark datasets demonstrate the proposed method can obviously increase retrieval performance in terms of mAP metric. The proposed method using 128-dimensionality representation can provide significantly higher mAPs than the DSFH, DWDF, and OSAH methods by 0.083, 0.043, and 0.022 on the Oxford5k dataset and by 0.195, 0.036, and 0.071 on the Paris6k dataset. The difference whitening method can conveniently transfer the deep learning model to a new task. Our method provided competitive performance compared with the existing aggregation methods and can retrieve scene images with similar colors, objects, and semantics.
Keywords:
Image retrieval
Deep feature
Difference whitening
Value-guided neural mechanisms
Multilayer feature aggregation histogram
Journal
IF:
4.3
Papers:
1.6K
Citations:
3.6K
Organization
Cited Papers
ShareSave
ShareSaveShareSaveShareSaveNeural mechanisms underlying the hierarchical construction of perceived aesthetic value.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAIShareSaveShareSave
View more