Triplet-Based Deep Hashing Network for Cross-Modal Retrieval

Deng, Cheng; Chen, Zhaojia; Liu, Xianglong; Gao, Xinbo; Tao, Dacheng

doi:10.1109/tip.2018.2821921

Cited by 346 publications

(151 citation statements)

References 38 publications

Supporting

Mentioning

147

Contrasting

Order By: Relevance

“…Recently, the amount of literatures have grown up considerably around the theme of hashing [12,13,32,45,45,46]. According to whether supervised information are involved in the learning phase, existing hashing models can be divided into two categories: supervised hashing methods and unsupervised hashing methods.…”

Section: Related Workmentioning

confidence: 99%

DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs

Yang

Liu

Deng

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

126

View full text Add to dashboard Cite

Due to the high storage and search efficiency, hashing has become prevalent for large-scale similarity search. Particularly, deep hashing methods have greatly improved the search performance under supervised scenarios. In contrast, unsupervised deep hashing models can hardly achieve satisfactory performance due to the lack of reliable supervisory similarity signals. To address this issue, we propose a novel deep unsupervised hashing model, dubbed Distill-Hash, which can learn a distilled data set consisted of data pairs, which have confidence similarity signals. Specifically, we investigate the relationship between the initial noisy similarity signals learned from local structures and the semantic similarity labels assigned by a Bayes optimal classifier. We show that under a mild assumption, some data pairs, of which labels are consistent with those assigned by the Bayes optimal classifier, can be potentially distilled. Inspired by this fact, we design a simple yet effective strategy to distill data pairs automatically and further adopt a Bayesian learning framework to learn hash functions from the distilled data set. Extensive experimental results on three widely used benchmark datasets show that the proposed DistillHash consistently accomplishes the stateof-the-art search performance.

show abstract

Section: Related Workmentioning

confidence: 99%

DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs

Yang

Liu

Deng

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

126

View full text Add to dashboard Cite

show abstract

“…The main goal in DCMH is to learn a set of hash codes such that the content similarities between different modalities is preserved in Hamming space. As such, a likelihood function [13], [20], [21] or margin-based loss function such as the triplet loss function [22], [23] needs to be incorporated into the DCMH framework to improve retrieval performance. In triplet-based arXiv:2004.03378v1 [cs.CV] 3 Apr 2020…”

Section: * Authors Contributed Equallymentioning

confidence: 99%

Error-Corrected Margin-Based Deep Cross-Modal Hashing for Facial Image Retrieval

Taherkhani

Talreja

Valenti

et al. 2020

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

Cross-modal hashing facilitates mapping of heterogeneous multimedia data into a common Hamming space, which can be utilized for fast and flexible retrieval across different modalities. In this paper, we propose a novel cross-modal hashing architecture-deep neural decoder cross-modal hashing (DNDCMH), which uses a binary vector specifying the presence of certain facial attributes as an input query to retrieve relevant face images from a database. The DNDCMH network consists of two separate components: an attribute-based deep cross-modal hashing (ADCMH) module, which uses a margin (m)-based loss function to efficiently learn compact binary codes to preserve similarity between modalities in the Hamming space, and a neural error correcting decoder (NECD), which is an error correcting decoder implemented with a neural network. The goal of NECD network in DNDCMH is to error correct the hash codes generated by ADCMH to improve the retrieval efficiency. The NECD network is trained such that it has an error correcting capability greater than or equal to the margin (m) of the margin-based loss function. This results in NECD can correct the corrupted hash codes generated by ADCMH up to the Hamming distance of m. We have evaluated and compared DNDCMH with state-of-the-art cross-modal hashing methods on standard datasets to demonstrate the superiority of our method.! DCMH [22], the inter-modal triplet embedding loss encourages the heterogeneous correlation across different modalities, and the intra-modal triplet loss encodes the discriminative power of the hash codes. Moreover, a regularization loss is used to apply adjacency consistency to ensure that the hash codes can keep the original similarities in Hamming space. However, in margin-based loss functions, some of the instances of different modalities of the same subject may not be close enough in Hamming space to guarantee all the correct retrievals. Therefore, it is important to bring the different modalities of the same subject closer to each other in Hamming space to improve the retrieval efficiency.In this work, we observe that in addition to the regular DCMH techniques [13], [24], [25], which exploit entropy maximization and quantization losses in the objective function of the DCMH, an error-correcting code (ECC) decoder can be used as an additional component to compensate for the heterogeneity gap and reduce the Hamming distance between the different modalities of the same subject in order to improve the cross-modal retrieval efficiency. We presume that the hash code generated by DCMH is a binary vector that is within a certain distance from a codeword of an ECC. When the hash code generated by DCMH is passed through an ECC decoder, the closest codeword to this hash code is found, which can be used as a final hash code for the retrieval process. In this process, the attribute hash code and image hash code of the same subject are forced to map to the same codeword, thereby reducing the distance of the corresponding hash codes. This brings more relevant facial images ...

show abstract

“…Hashing-based approximate nearest-neighbor search has attracted much attention in the literature, owing to its high search performance and low computational requirements [3][4][5][6]. Locality-sensitive hashing (LSH) is the most fundamental concept in such hashing research [7], which has led many studies to focus on finding ways to generate compact hash codes by exploiting different techniques, including (semi-) supervised learning [8][9][10], non-linear mapping [5,8,[11][12][13][14][15], discrete optimization [12,[16][17][18], multiple features [2,19], and bit selection [20,21].…”

Section: Introductionmentioning

confidence: 99%

Fast distributed video deduplication via locality-sensitive hashing with similarity ranking

Xia

et al. 2019

J Image Video Proc.

View full text Add to dashboard Cite

The exponentially growing amount of video data being produced has led to tremendous challenges for video deduplication technology. Nowadays, many different deduplication approaches are being rapidly developed, but they are generally slow and their identification processes are somewhat inaccurate. Till now, there is rare work that studies the generic hash-based distributed framework and the efficient similarity ranking strategy for video deduplication. This paper proposes a flexible and fast distributed video deduplication framework based on hash codes. It is able to support the hash table indexing using any existing hashing algorithm in a distributed environment and can efficiently rank the candidate videos by exploring the similarities among the key frames over multiple tables using MapReduce strategy. Our experiments with a popular large-scale dataset demonstrate that the proposed framework can achieve satisfactory video deduplication performance.

show abstract

Triplet-Based Deep Hashing Network for Cross-Modal Retrieval

Cited by 346 publications

References 38 publications

DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs

DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs

Error-Corrected Margin-Based Deep Cross-Modal Hashing for Facial Image Retrieval

Fast distributed video deduplication via locality-sensitive hashing with similarity ranking

Contact Info

Product

Resources

About