Unsupervised Rank-Preserving Hashing for Large-Scale Image Retrieval
We propose an unsupervised hashing method which aims to produce binary codes that preserve the ranking induced by a real-valued representation. Such compact hash codes enable the complete elimination of real-valued feature storage and allow for significant reduction of the computation complexity and storage cost of large-scale image retrieval applications. Specifically, we learn a neural network-based model, which transforms the input representation into a binary representation. We formalize the training objective of the network in an intuitive and effective way, considering each training sample as a query and aiming to obtain the same retrieval results using the produced hash codes as those obtained with the original features. This training formulation directly optimizes the hashing model for the target usage of the hash codes it produces. We further explore the addition of a decoder trained to obtain an approximated reconstruction of the original features. At test time, we retrieved the most promising database samples with an efficient graph-based search procedure using only our hash codes and perform re-ranking using the reconstructed features, thus without needing to access the original features at all. Experiments conducted on multiple publicly available large-scale datasets show that our method consistently outperforms all compared state-of-the-art unsupervised hashing methods and that the reconstruction procedure can effectively boost the search accuracy with a minimal constant additional cost.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderImage RetrievalRe-RankingRetrievalSimilar Papers 제목 키워드 기반
Ranking Preserving Hashing for Fast Similarity Search
Hashing method becomes popular for large scale similarity search due to its storage and computational efficiency. Many machine learning techniques, ranging from unsupervised to supervised, have been proposed to design co…
Computational EfficiencyObject Detection based Deep Unsupervised Hashing
Recently, similarity-preserving hashing methods have been extensively studied for large-scale image retrieval. Compared with unsupervised hashing, supervised hashing methods for labeled data have usually better performan…
Image RetrievalNovel Object DetectionObjectobject-detection+2Ordinal Constrained Binary Code Learning for Nearest Neighbor Search
Recent years have witnessed extensive attention in binary code learning, a.k.a. hashing, for nearest neighbor search problems. It has been seen that high-dimensional data points can be quantized into binary codes to give…
RetrievalSmall Data Image ClassificationViT2Hash: Unsupervised Information-Preserving Hashing
Unsupervised image hashing, which maps images into binary codes without supervision, is a compressor with a high compression rate. Hence, how to preserving meaningful information of the original data is a critical proble…
QuantizationUnsupervised Semantic Deep Hashing
In recent years, deep hashing methods have been proved to be efficient since it employs convolutional neural network to learn features and hashing codes simultaneously. However, these methods are mostly supervised. In re…
Deep HashingImage RetrievalQuantizationRetrieval