Learning Binary Codes for High-Dimensional Data Using Bilinear Projections

Gong, Yunchao; Kumar, Sanjiv; Rowley, Henry A.; Lazebnik, Svetlana

doi:10.1109/cvpr.2013.69

Cited by 165 publications

(158 citation statements)

References 27 publications

Supporting

Mentioning

157

Contrasting

Order By: Relevance

“…In this experiment (Table V) we compare the behavior of retrieval performance for different lengths of the hash code (for m-kmeans-t 1 ) and for different values of n nearest neighbors (for [60] 0.381 0.225 -PCAHash [54] 0.528 0.239 -LSH [61] 0.431 0.239 -SKLSH [62] 0.241 0.134 -SH [2] 0.522 0.232 -SRBM [63] 0.516 0.212 -UTH [31] 0.571 0.240 -m-k-means-n 1 (n = m-kmeans-n 1 ). Experiments were made for SIFT1M for different values of recall@R. Fig.…”

Section: Results Varying Hash Code Length and Nmentioning

confidence: 99%

Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases

Ercoli

Bertini

Bimbo

2017

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-In this paper, we present an efficient method for visual descriptors retrieval based on compact hash codes computed using a multiple k-means assignment. The method has been applied to the problem of approximate nearest neighbor (ANN) search of local and global visual content descriptors, and it has been tested on different datasets: three large scale standard datasets of engineered features of up to one billion descriptors (BIGANN) and, supported by recent progress in convolutional neural networks (CNNs), on CIFAR-10, MNIST, INRIA Holidays, Oxford 5K, and Paris 6K datasets; also, the recent DEEP1B dataset, composed by one billion CNN-based features, has been used. Experimental results show that, despite its simplicity, the proposed method obtains a very high performance that makes it superior to more complex state-ofthe-art methods.Index Terms-Convolutional neural network (CNN), hashing, nearest neighbor search, retrieval, SIFT.

show abstract

Section: Results Varying Hash Code Length and Nmentioning

confidence: 99%

Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases

Ercoli

Bertini

Bimbo

2017

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…For example, the introduced hashing techniques can be applied to large-scale mobile video retrieval [29]. Another useful application of the hashing methods would be compressing the high dimensional features into short binary codes, which could significantly speed up the potential tasks, such as the large scale ImageNet image classification [12], [28].…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Hashing on Nonlinear Manifolds

Shen

Shi

et al. 2015

IEEE Trans. on Image Process.

125

View full text Add to dashboard Cite

Abstract-Learning based hashing methods have attracted considerable attention due to their ability to greatly increase the scale at which existing algorithms may operate. Most of these methods are designed to generate binary codes preserving the Euclidean similarity in the original space. Manifold learning techniques, in contrast, are better able to model the intrinsic structure embedded in the original high-dimensional data. The complexities of these models, and the problems with out-ofsample data, have previously rendered them unsuitable for application to large-scale embedding, however.In this work, how to learn compact binary embeddings on their intrinsic manifolds is considered. In order to address the abovementioned difficulties, an efficient, inductive solution to the outof-sample data problem, and a process by which non-parametric manifold learning may be used as the basis of a hashing method is proposed. The proposed approach thus allows the development of a range of new hashing techniques exploiting the flexibility of the wide variety of manifold learning approaches available. It is particularly shown that hashing on the basis of t-SNE [41] outperforms state-of-the-art hashing methods on large-scale benchmark datasets, and is very effective for image classification with very short code lengths. The proposed hashing framework is shown to be easily improved, for example, by minimizing the quantization error with learned orthogonal rotations. In addition, a supervised inductive manifold hashing framework is developed by incorporating the label information, which is shown to greatly advance the semantic retrieval performance.Index Terms-Hashing, binary code learning, manifold learning, image retrieval.

show abstract

“…It is worthwhile to highlight several properties of the proposed method: (1) Different with global representation based hashing, LFBC directly learns hashing function from local features and simultaneously preserves pairwise F2F and I2C structure, which is proved to be more effective for accurate retrieval. (2) Inspired by [2,4], bilinear projection based hashing function is adopted in our method. Thus, the complexity of the eigen-decomposition, which is the cubic form of the dimensionality, will be significantly reduced.…”

mentioning

confidence: 99%

Local Feature Binary Coding for Approximate Nearest Neighbor Search

Liu

Yu²,

Shao³

2015

Procedings of the British Machine Vision Conference 2015

View full text Add to dashboard Cite

Figure 1: The illustration of the working flow of LFBC learning. The algorithm intends to preserve the pairwise F2F structure and the I2C distances and outputs the optimal bilinear projection matrices Θ 1 and Θ 2 .The potential value of hashing techniques has led to it becoming one of the most active research areas in computer vision and multimedia. However, most existing hashing methods for image search and retrieval are based on global representations, e.g., GIST [3], which lack the analysis of the intrinsic geometric property of local features and heavily limit the effectiveness of the hash code. In this paper, we propose an supervised local feature hashing framework, i.e., Local Feature Binary Coding (LF-BC), for visual similarity search, in which the feature-to-feature (F2F) and image-to-class (I2C) structures are successfully preserved and combined together. Specifically, the F2F structure considers the pairwise relationship between local features in the original feature space. While, from a higher-level aspect, I2C structure reflects the connection between images and their corresponding classes, which is derived from [1]. The outline of the proposed method is illustrated in Fig. 1. It is worthwhile to highlight several properties of the proposed method: (1) Different with global representation based hashing, LFBC directly learns hashing function from local features and simultaneously preserves pairwise F2F and I2C structure, which is proved to be more effective for accurate retrieval. (2) Inspired by [2,4], bilinear projection based hashing function is adopted in our method. Thus, the complexity of the eigen-decomposition, which is the cubic form of the dimensionality, will be significantly reduced. The corresponding integrated LFBC algorithm is depicted in Algorithm 1. Algorithm 1 Local Feature Binary Coding (LFBC)Input: Local feature set of each training image X i = {X i1 , · · · , X im i } in matrix form, i = 1, · · · , n, the whole local feature set F = X i , the parameter k for pairwise structure preserving, the number of centroids K in K-means and the label information function C(·) : F → {1, · · · ,C}. Output: The bilinear projection matrices Θ 1 and Θ 2 .1: Construct local feature pairing set P = {(i, j)|X i , X j ∈ F} and their corresponding pairwise labels i j = {−1, +1}, where, and i j = −1 otherwise; 2: Employ the K-means clustering algorithm on the set of local features of each class C(X i )=c X i , c = 1, · · · ,C; Optimize Θ 1 and Θ 2 alternately; 7: until the objective function L(Θ 1 , Θ 2 ) converges.In the retrieval phase, considering that our method is specifically designed for local features, the original Hamming Ranking and Hamming Table cannot be directly applied to local features for visual index- ing. Thus, in this paper, we also introduce an indexing/searching scheme called Local Hashing Voting (LHV) as shown in Fig. 2, which has been demonstrated to be efficient and accurate for image similarity search in our experiments. For instance, given a bucket with hash code [1,1,-1,-1...

show abstract

Learning Binary Codes for High-Dimensional Data Using Bilinear Projections

Cited by 165 publications

References 27 publications

Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases

Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases

Hashing on Nonlinear Manifolds

Local Feature Binary Coding for Approximate Nearest Neighbor Search

Contact Info

Product

Resources

About