IEEE Signal Processing Letters · 2024 · 10 citations · 30 references
ComputingComputer ScienceComputer VisionInformation RetrievalMachine LearningDeep LearningHash FunctionsHash TablesImage Feature EngineeringImage RetrievalRepresentation LearningBenchmark DatasetsCosine SimilarityData AugmentationDeep Image FeaturesDiscriminative FunctionsHashingSimilarity MetricsTriplet Loss
Deep hashing enhances image retrieval accuracy by integrating hash encoding with deep neural networks. However, existing unsupervised deep hashing methods primarily rely on the rotational invariance of images to construct triplets, resulting in triplets that are unsatisfactory in both reliability and quantity. Additionally, some methods fail to adequately consider the relative similarity information between samples. To overcome these limitations, we propose a novel unsupervised deep triplet hashing method for image retrieval (abbreviated as UDTrHash). UDTrHash utilizes the extremal cosine similarity of deep features of images to construct more reliable first type triplets and expands the formed triplets through data augmentation strategies to introduce a larger number of triplets. Furthermore, we design a new triplet loss function to enhance the discriminative ability of the generated hash codes. Extensive experiments demonstrate that UDTrHash exhibits superior performance on three public benchmark datasets such as MIRFlickr25K compared to existing state-of-the-art hashing methods.
30
Tat‐Seng Chua, Jinhui Tang, Richang Hong et al. · 2009 · 3K citations
Semantic Structure-based Unsupervised Deep Hashing
Erkun Yang, Cheng Deng, Tongliang Liu et al. · 2018 · 170 citations · Full text
DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs
Erkun Yang, Tongliang Liu, Cheng Deng et al. · 2019 · 164 citations
Auto-Encoding Twin-Bottleneck Hashing
Yuming Shen, Jie Qin, Jiaxin Chen et al. · 2020 · 132 citations