Journal ArticleDOI
Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval
Reads0
Chats0
TLDR
This paper addresses the problem of learning similarity-preserving binary codes for efficient similarity search in large-scale image collections by proposing a simple and efficient alternating minimization algorithm, dubbed iterative quantization (ITQ), and demonstrating an application of ITQ to learning binary attributes or "classemes" on the ImageNet data set.Abstract:
This paper addresses the problem of learning similarity-preserving binary codes for efficient similarity search in large-scale image collections. We formulate this problem in terms of finding a rotation of zero-centered data so as to minimize the quantization error of mapping this data to the vertices of a zero-centered binary hypercube, and propose a simple and efficient alternating minimization algorithm to accomplish this task. This algorithm, dubbed iterative quantization (ITQ), has connections to multiclass spectral clustering and to the orthogonal Procrustes problem, and it can be used both with unsupervised data embeddings such as PCA and supervised embeddings such as canonical correlation analysis (CCA). The resulting binary codes significantly outperform several other state-of-the-art methods. We also show that further performance improvements can result from transforming the data with a nonlinear kernel mapping prior to PCA or CCA. Finally, we demonstrate an application of ITQ to learning binary attributes or "classemes" on the ImageNet data set.read more
Citations
More filters
Proceedings ArticleDOI
One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching
Khoa Doan,Peng Yang,Ping Li +2 more
TL;DR: The task of learning balanced codes with low quantization error is re-formulated as matching the learned distribution of the continuous codes to a pre-defined discrete, uniform distribution, equivalent to minimizing the distance between two distributions.
Journal ArticleDOI
Study on 2D Feature-Based Hash Learning
TL;DR: A comparison study on 1D and 2D feature-based hashing methods and attempt to theoretically and experimentally analyse the differences in using 1D or 2D features in hashing to obtain three main conclusions.
Posted Content
Deep Discrete Hashing with Self-supervised Pairwise Labels
TL;DR: Experimental results on standard datasets demonstrate that the proposed novel unsupervised deep hashing method, named Deep Discrete Hashing (DDH), significantly outperforms existing hashing methods by large margin in terms of mAP for image retrieval and object recognition.
Posted Content
Fast Class-wise Updating for Online Hashing
TL;DR: A novel supervised online hashing scheme is proposed to address the above two challenges by introducing a novel and efficient inner product operation, and quantitatively demonstrated that the collective effort of class-wise updating and semi-relaxation optimization provides a superior performance comparing to various state-of-the-art methods.
Journal ArticleDOI
Multi-class joint subspace learning for cross-modal retrieval
TL;DR: The multi-class joint subspace learning algorithm (MJSL) is proposed to distinct the different classes and mine the potential shared information of semantic overlap as much as possible, and outperforms several state-of-the-art cross-modal retrieval algorithms.
References
More filters
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Dissertation
Learning Multiple Layers of Features from Tiny Images
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.
Journal Article
LIBLINEAR: A Library for Large Linear Classification
TL;DR: LIBLINEAR is an open source library for large-scale linear classification that supports logistic regression and linear support vector machines and provides easy-to-use command-line tools and library calls for users and developers.
Journal ArticleDOI
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
Aude Oliva,Antonio Torralba +1 more
TL;DR: The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.