Self-supervised Consistent Quantization For Fully Unsupervised Image Retrieval

Abstract

Unsupervised image retrieval aims to learn an efficient retrieval system without expensive data annotations, but most existing methods rely heavily on handcrafted feature descriptors or pre-trained feature extractors. To minimize human supervision, recent advance proposes deep fully unsupervised image retrieval aiming at training a deep model from scratch to jointly optimize visual features and quantization codes. However, existing approach mainly focuses on instance contrastive learning without considering underlying semantic structure information, resulting in sub-optimal performance. In this work, we propose a novel self-supervised consistent quantization approach to deep fully unsupervised image retrieval, which consists of part consistent quantization and global consistent quantization. In part consistent quantization, we devise part neighbor semantic consistency learning with codeword diversity regularization. This allows to discover underlying neighbor structure information of s

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywu2022self

Related papers

• Self-supervised Product Quantization For Deep Unsupervised Image Retrieval (2021)13.44
• Weakly Supervised Deep Hyperspherical Quantization For Image Retrieval (2024)10.04
• Generalized Product Quantization Network For Semi-supervised Image Retrieval (2020)12.17
• Transformer-based Clipped Contrastive Quantization Learning For Unsupervised Image Retrieval (2024)5.84
• End-to-end Supervised Product Quantization For Image Search And Retrieval (2017)13.05
• Orthonormal Product Quantization Network For Scalable Face Image Retrieval (2021)8.60
• Beyond Product Quantization: Deep Progressive Quantization For Image Retrieval (2019)12.95
• Simultaneous Compression And Quantization: A Joint Approach For Efficient Unsupervised Hashing (2018)7.50