Weakly Supervised Deep Hyperspherical Quantization For Image Retrieval

Abstract

Deep quantization methods have shown high efficiency on large-scale image retrieval. However, current models heavily rely on ground-truth information, hindering the application of quantization in label-hungry scenarios. A more realistic demand is to learn from inexhaustible uploaded images that are associated with informal tags provided by amateur users. Though such sketchy tags do not obviously reveal the labels, they actually contain useful semantic information for supervising deep quantization. To this end, we propose Weakly-Supervised Deep Hyperspherical Quantization (WSDHQ), which is the first work to learn deep quantization from weakly tagged images. Specifically, 1) we use word embeddings to represent the tags and enhance their semantic information based on a tag correlation graph. 2) To better preserve semantic information in quantization codes and reduce quantization error, we jointly learn semantics-preserving embeddings and supervised quantizer on hypersphere by employing a

Stats

• citations12
• S2 citations—
• github stars6
• HF likes0
• heat score10.04
• arxiv keywang2024weakly

Related papers

• Self-supervised Consistent Quantization For Fully Unsupervised Image Retrieval (2022)0.00
• Self-supervised Product Quantization For Deep Unsupervised Image Retrieval (2021)13.44
• End-to-end Supervised Product Quantization For Image Search And Retrieval (2017)13.05
• Hihpq: Hierarchical Hyperbolic Product Quantization For Unsupervised Image Retrieval (2024)6.77
• Generalized Product Quantization Network For Semi-supervised Image Retrieval (2020)12.17
• Weakly Supervised Deep Image Hashing Through Tag Embeddings (2018)11.29
• Deep Supervised Hashing Leveraging Quadratic Spherical Mutual Information For Content-based Image Retrieval (2019)0.00
• Beyond Product Quantization: Deep Progressive Quantization For Image Retrieval (2019)12.95