Joint Cluster Unary Loss For Efficient Cross-modal Hashing

Abstract

With the rapid growth of various types of multimodal data, cross-modal deep hashing has received broad attention for solving cross-modal retrieval problems efficiently. Most cross-modal hashing methods follow the traditional supervised hashing framework in which the \(O(n^2)\) data pairs and \(O(n^3)\) data triplets are generated for training, but the training procedure is less efficient because the complexity is high for large-scale dataset. To address these issues, we propose a novel and efficient cross-modal hashing algorithm in which the unary loss is introduced. First of all, We introduce the Cross-Modal Unary Loss (CMUL) with \(O(n)\) complexity to bridge the traditional triplet loss and classification-based unary loss. A more accurate bound of the triplet loss for structured multilabel data is also proposed in CMUL. Second, we propose the novel Joint Cluster Cross-Modal Hashing (JCCH) algorithm for efficient hash learning, in which the CMUL is involved. The resultant hashcodes f

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyzhang2019joint

Related papers

• Weakly-paired Cross-modal Hashing (2019)0.00
• Semantic Cluster Unary Loss For Efficient Deep Hashing (2018)7.81
• Unsupervised Multi-modal Hashing For Cross-modal Retrieval (2019)8.35
• Fusion-supervised Deep Cross-modal Hashing (2019)8.60
• Deep Cross-modal Hashing With Hashing Functions And Unified Hash Codes Jointly Learning (2019)14.23
• Cluster-wise Unsupervised Hashing For Cross-modal Similarity Search (2019)11.39
• Deep Class-guided Hashing For Multi-label Cross-modal Retrieval (2024)6.20
• Correlation Hashing Network For Efficient Cross-modal Retrieval (2016)11.67