Deep Unsupervised Hashing With Latent Semantic Components
2022 · Qinghong Lin, Xiaojun Chen, Qin Zhang, et al.
Abstract
Deep unsupervised hashing has been appreciated in the regime of image retrieval. However, most prior arts failed to detect the semantic components and their relationships behind the images, which makes them lack discriminative power. To make up the defect, we propose a novel Deep Semantic Components Hashing (DSCH), which involves a common sense that an image normally contains a bunch of semantic components with homology and co-occurrence relationships. Based on this prior, DSCH regards the semantic components as latent variables under the Expectation-Maximization framework and designs a two-step iterative algorithm with the objective of maximum likelihood of training data. Firstly, DSCH constructs a semantic component structure by uncovering the fine-grained semantics components of images with a Gaussian Mixture Modal~(GMM), where an image is represented as a mixture of multiple components, and the semantics co-occurrence are exploited. Besides, coarse-grained semantics components, are
Authors
(none)
Tags
Stats
Related papers
- Deep Hashing With Semantic Hash Centers For Image Retrieval (2025)2.26
- Unsupervised Semantic Deep Hashing (2018)10.48
- Unsupervised Hashing With Semantic Concept Mining (2022)7.50
- SSDH: Semi-supervised Deep Hashing For Large Scale Image Retrieval (2016)15.40
- Exploring Auxiliary Context: Discrete Semantic Transfer Hashing For Scalable Image Retrieval (2019)15.88
- Self-supervised Asymmetric Deep Hashing With Margin-scalable Constraint (2020)0.00
- Deep Collaborative Discrete Hashing With Semantic-invariant Structure (2019)8.09
- Deep Self-adaptive Hashing For Image Retrieval (2021)8.35