Beyond Product Quantization: Deep Progressive Quantization For Image Retrieval

Abstract

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the retraining of model is usually unavoidable when the code length changes. In this work, we propose a deep progressive quantization (DPQ) model, as an alternative to PQ, for large scale image retrieval. DPQ learns the quantization codes sequentially and approximates the original feature space progressively. Therefore, we can train the quantization codes with different code lengths simultaneously. Specifically, we first utilize the label information for guiding the learning of visual features, and then apply several quantization blocks to progressively approach the visual features. Each quantization block is designed to be a layer of a convolutional neural network, and the whole framework can be trained in an end-to-end manner. Experimental results on the ben

Stats

• citations23
• S2 citations—
• github stars19
• HF likes0
• heat score12.95
• arxiv keygao2019beyond

Related papers

• End-to-end Supervised Product Quantization For Image Search And Retrieval (2017)13.05
• Adversarial Attack On Deep Product Quantization Network For Image Retrieval (2020)11.29
• Generalized Product Quantization Network For Semi-supervised Image Retrieval (2020)12.17
• Matching-oriented Product Quantization For Ad-hoc Retrieval (2021)2.29
• Self-supervised Product Quantization For Deep Unsupervised Image Retrieval (2021)13.44
• Orthonormal Product Quantization Network For Scalable Face Image Retrieval (2021)8.60
• Jointly Optimizing Query Encoder And Product Quantization To Improve Retrieval Performance (2021)12.74
• Hihpq: Hierarchical Hyperbolic Product Quantization For Unsupervised Image Retrieval (2024)6.77