Probability Weighted Compact Feature For Domain Adaptive Retrieval
2020 · Fuxiang Huang, Lei Zhang, Yang Yang, et al.
Abstract
Domain adaptive image retrieval includes single-domain retrieval and cross-domain retrieval. Most of the existing image retrieval methods only focus on single-domain retrieval, which assumes that the distributions of retrieval databases and queries are similar. However, in practical application, the discrepancies between retrieval databases often taken in ideal illumination/pose/background/camera conditions and queries usually obtained in uncontrolled conditions are very large. In this paper, considering the practical application, we focus on challenging cross-domain retrieval. To address the problem, we propose an effective method named Probability Weighted Compact Feature Learning (PWCF), which provides inter-domain correlation guidance to promote cross-domain retrieval accuracy and learns a series of compact binary codes to improve the retrieval speed. First, we derive our loss function through the Maximum A Posteriori Estimation (MAP): Bayesian Perspective (BP) induced focal-triple
Authors
(none)
Tags
Stats
Related papers
- Coarse-to-fine: Learning Compact Discriminative Representation For Single-stage Image Retrieval (2023)9.35
- Automatic Feature Weight Determination Using Indexing And Pseudo-relevance Feedback For Multi-feature Content-based Image Retrieval (2018)0.00
- Unsupervised Part-based Weighting Aggregation Of Deep Convolutional Features For Image Retrieval (2017)14.91
- Feature Representation Learning For Unsupervised Cross-domain Image Retrieval (2022)11.46
- From Selective Deep Convolutional Features To Compact Binary Representations For Image Retrieval (2018)10.35
- Simultaneous Feature Aggregating And Hashing For Compact Binary Code Learning (2019)9.92
- Matrix Factorization-based Clustering Of Image Features For Bandwidth-constrained Information Retrieval (2016)0.00
- Adaptive Co-weighting Deep Convolutional Features For Object Retrieval (2018)4.52