Adaptive Co-weighting Deep Convolutional Features For Object Retrieval

Abstract

Aggregating deep convolutional features into a global image vector has attracted sustained attention in image retrieval. In this paper, we propose an efficient unsupervised aggregation method that uses an adaptive Gaussian filter and an elementvalue sensitive vector to co-weight deep features. Specifically, the Gaussian filter assigns large weights to features of region-of-interests (RoI) by adaptively determining the RoI's center, while the element-value sensitive channel vector suppresses burstiness phenomenon by assigning small weights to feature maps with large sum values of all locations. Experimental results on benchmark datasets validate the proposed two weighting schemes both effectively improve the discrimination power of image vectors. Furthermore, with the same experimental setting, our method outperforms other very recent aggregation approaches by a considerable margin.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keywang2018adaptive

Related papers

• Unsupervised Part-based Weighting Aggregation Of Deep Convolutional Features For Image Retrieval (2017)14.91
• Aggregated Deep Local Features For Remote Sensing Image Retrieval (2019)14.11
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Co-occurrence Of Deep Convolutional Features For Image Search (2020)9.76
• Simultaneous Feature Aggregating And Hashing For Large-scale Image Search (2017)10.61
• Selective Convolutional Descriptor Aggregation For Fine-grained Image Retrieval (2016)19.37
• Aggregating Binary Local Descriptors For Image Retrieval (2016)7.16
• Unsupervised Semantic-based Aggregation Of Deep Convolutional Features (2018)11.85