Vector of Locally and Adaptively Aggregated Descriptors for Image Feature Representation

作者：

Highlights：

• VLAAD framework uses adaptive weighting mechanism to improve the discriminative power of feature representations.

• VLAAD framework is implemented by the Weighted NetVLAD and Gated NetVLAD.

• Competitive performance has been achieved comparing with the state-of-the-art.

摘要

•VLAAD framework uses adaptive weighting mechanism to improve the discriminative power of feature representations.•VLAAD framework is implemented by the Weighted NetVLAD and Gated NetVLAD.•Competitive performance has been achieved comparing with the state-of-the-art.

论文关键词：VLAD,Deep learning,Weighting scheme,Gating scheme,Feature representation

论文评审过程：Received 1 July 2020, Revised 13 January 2021, Accepted 23 February 2021, Available online 18 March 2021, Version of Record 28 March 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107952