SCRATCH: A Scalable Discrete Matrix Factorization Hashing Framework for Cross-Modal Retrieval

Chen, Zhen-Duo; Li, Chuan-Xiang; Luo, Xin; Nie, Liqiang; Zhang, Wei; Xu, Xin-Shun

doi:10.1109/tcsvt.2019.2911359

Cited by 96 publications

(41 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the two datasets described above, we compared DTCH with eight cross-modal hashing methods that have been proposed in recent years: cross-view hashing (CVH) [ 13 ], intermedia hashing (IMH) [ 14 ], latent semantic sparse hashing (LSSH) [ 15 ], semantic correlation maximization (SCM) [ 16 ], discrete cross-modal hashing (DCH) [ 4 ], fast discrete cross-modal hashing (FDCH) [ 26 ], scalable discrete matrix factorization hashing (SCRATCH) [ 17 ], and two-step cross-modal hashing (TECH) [ 18 ]. Among these, CVH, IMH, and LSSH are unsupervised methods and the others are supervised methods.…”

Section: Methodsmentioning

confidence: 99%

“…However, SDH adopts the bitwise learning strategy to generate binary codes, making it time-consuming. Chen et al [ 17 ] proposed a scalable cross-modal hashing method in which matrix factorization is applied to the cross-modal field. Generally speaking, the retrieval accuracies of supervised learning methods are significantly higher than those of unsupervised methods owing to the exploitation of label information.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Discrete Two‐Step Cross‐Modal Hashing through the Exploitation of Pairwise Relations

Shao-hua

Kang

Liu

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The cross-modal hashing method can map heterogeneous multimodal data into a compact binary code that preserves semantic similarity, which can significantly enhance the convenience of cross-modal retrieval. However, the currently available supervised cross-modal hashing methods generally only factorize the label matrix and do not fully exploit the supervised information. Furthermore, these methods often only use one-directional mapping, which results in an unstable hash learning process. To address these problems, we propose a new supervised cross-modal hash learning method called Discrete Two-step Cross-modal Hashing (DTCH) through the exploitation of pairwise relations. Specifically, this method fully exploits the pairwise similarity relations contained in the supervision information: for the label matrix, the hash learning process is stabilized by combining matrix factorization and label regression; for the pairwise similarity matrix, a semirelaxed and semidiscrete strategy is adopted to potentially reduce the cumulative quantization errors while improving the retrieval efficiency and accuracy. The approach further combines an exploration of fine-grained features in the objective function with a novel out-of-sample extension strategy to enable the implicit preservation of consistency between the different modal distributions of samples and the pairwise similarity relations. The superiority of our method was verified through extensive experiments using two widely used datasets.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Discrete Two‐Step Cross‐Modal Hashing through the Exploitation of Pairwise Relations

Shao-hua

Kang

Liu

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…To evaluate the efficiency and effectiveness of SDDH, we compare SDDH with seven cross-modal hashing methods, in- cluding unsupervised method such as CMFH [2] and FSH [8], and supervised methods such as DCH [3], ADCH [12], GSPH [10], LCMFH [13] and SCRATCH [14]. For the proposed method, we empirically set λ = 5e − 4, γ = 1000, ξ = 0.001 and T = 6 for all three databases.…”

Section: Databases and Experimental Settingsmentioning

confidence: 99%

“…Wang et al [13] directly utilized the semantic labels for hash code classification. Moreover, recent researches [3,14] demonstrated that reducing the quantization errors by generating the hash codes under the discrete constraints is an effective way to facilitate the retrieval performance of supervised methods. For example, Shen et al [15] proposed a discrete cyclic coordinate descent method to learn binary codes bit by bit, which requires excessive computation in learning process.…”

Section: Introductionmentioning

confidence: 99%

Scalable Discriminative Discrete Hashing For Large-Scale Cross-Modal Retrieval

Qin

Zhang

Zhu

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Cross-modal hashing has received increasing research attentions due to its less storage and efficient retrieval. However, most existing cross-modal hashing methods focus only on exploring multi-modal information, while underestimate the significance of local and Euclidean structure information on the hashing learning procedure. In this paper, we propose a supervised discrete-based cross-modal hashing method, named Scalable Discriminative Discrete Hashing (SDDH), for cross-modal retrieval, where 1) the discrete hash codes are directly obtained by multi-modal features and semantic labels so that the quantization errors are dramatically reduced, and 2) the discrete hash codes simultaneously preserve the heterogeneous similarity and manifold information in the original space by employing matrix factoring with orthogonal and balanced constraints. Moreover, an efficient optimization is introduced to tackle the discrete solution, which makes the SDDH scalable to large-scale cross-modal retrieval. Empirical results on three widely-used benchmark databases clearly demonstrate the effectiveness and efficiency of the proposed method in comparison with state-of-the-arts.

show abstract

“…Therefore, hashing methods can accelerate ANN search procedures and save on storage. Recently, hashing methods have been applied in the area of computer vision and machine learning [3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Top Position Sensitive Ordinal Relation Preserving Bitwise Weight for Image Retrieval

et al. 2020

View full text Add to dashboard Cite

In recent years, binary coding methods have become increasingly popular for tasks of searching approximate nearest neighbors (ANNs). High-dimensional data can be quantized into binary codes to give an efficient similarity approximation via a Hamming distance. However, most of existing schemes consider the importance of each binary bit as the same and treat training samples at different positions equally, which causes many data pairs to share the same Hamming distance and a larger retrieval loss at the top position. To handle these problems, we propose a novel method dubbed by the top-position-sensitive ordinal-relation-preserving bitwise weight (TORBW) method. The core idea is to penalize data points without preserving an ordinal relation at the top position of a ranking list more than those at the bottom and assign different weight values to their binary bits according to the distribution of query data. Specifically, we design an iterative optimization mechanism to simultaneously learn binary codes and bitwise weights, which makes their learning processes related to each other. When the iterative procedure converges, the binary codes and bitwise weights are effectively adapted to each other. To reduce the training complexity, we relax the discrete constraints of both the binary codes and the indicator function. Furthermore, we pretrain a tensor ordinal graph to decrease the time consumption of computing a relative similarity relationship among data points. Experimental results on three large-scale ANN search benchmark datasets, i.e., SIFT1M, GIST1M, and Cifar10, show that the proposed TORBW method can achieve superior performance over state-of-the-art approaches.

show abstract

SCRATCH: A Scalable Discrete Matrix Factorization Hashing Framework for Cross-Modal Retrieval

Cited by 96 publications

References 52 publications

Discrete Two‐Step Cross‐Modal Hashing through the Exploitation of Pairwise Relations

Discrete Two‐Step Cross‐Modal Hashing through the Exploitation of Pairwise Relations

Scalable Discriminative Discrete Hashing For Large-Scale Cross-Modal Retrieval

Top Position Sensitive Ordinal Relation Preserving Bitwise Weight for Image Retrieval

Contact Info

Product

Resources

About