Random VLAD based Deep Hashing for Efficient Image Retrieval
This work addresses the problem of efficient image retrieval for large-scale applications, representing an incremental improvement over existing methods.
The paper tackled efficient large-scale image retrieval by proposing RV-SSDH, a deep hashing algorithm that integrates a random VLAD layer into neural networks, which significantly outperformed baselines like NetVLAD and SSDH in experiments.
Image hash algorithms generate compact binary representations that can be quickly matched by Hamming distance, thus become an efficient solution for large-scale image retrieval. This paper proposes RV-SSDH, a deep image hash algorithm that incorporates the classical VLAD (vector of locally aggregated descriptors) architecture into neural networks. Specifically, a novel neural network component is formed by coupling a random VLAD layer with a latent hash layer through a transform layer. This component can be combined with convolutional layers to realize a hash algorithm. We implement RV-SSDH as a point-wise algorithm that can be efficiently trained by minimizing classification error and quantization loss. Comprehensive experiments show this new architecture significantly outperforms baselines such as NetVLAD and SSDH, and offers a cost-effective trade-off in the state-of-the-art. In addition, the proposed random VLAD layer leads to satisfactory accuracy with low complexity, thus shows promising potentials as an alternative to NetVLAD.