Self-supervised Product Quantization For Deep Unsupervised Image Retrieval

Abstract

Supervised deep learning-based hash and vector quantization are enabling fast and large-scale image retrieval systems. By fully exploiting label annotations, they are achieving outstanding retrieval performances compared to the conventional methods. However, it is painstaking to assign labels precisely for a vast amount of training data, and also, the annotation process is error-prone. To tackle these issues, we propose the first deep unsupervised image retrieval method dubbed Self-supervised Product Quantization (SPQ) network, which is label-free and trained in a self-supervised manner. We design a Cross Quantized Contrastive learning strategy that jointly learns codewords and deep visual descriptors by comparing individually transformed images (views). Our method analyzes the image contents to extract descriptive features, allowing us to understand image representations for accurate retrieval. By conducting extensive experiments on benchmarks, we demonstrate that the proposed method

Stats

• citations61
• S2 citations—
• github stars0
• HF likes0
• heat score13.44
• arxiv keyjang2021self

Related papers

• Generalized Product Quantization Network For Semi-supervised Image Retrieval (2020)12.17
• End-to-end Supervised Product Quantization For Image Search And Retrieval (2017)13.05
• Self-supervised Consistent Quantization For Fully Unsupervised Image Retrieval (2022)0.00
• Beyond Product Quantization: Deep Progressive Quantization For Image Retrieval (2019)12.95
• Weakly Supervised Deep Hyperspherical Quantization For Image Retrieval (2024)10.04
• Hihpq: Hierarchical Hyperbolic Product Quantization For Unsupervised Image Retrieval (2024)6.77
• Orthonormal Product Quantization Network For Scalable Face Image Retrieval (2021)8.60
• Matching-oriented Product Quantization For Ad-hoc Retrieval (2021)2.29