A Survey on Deep Hashing Methods

Luo, Xiangfeng; Wang, Haixin; Wu, Daqing; Chen, Chong; Deng, Mei; Huang, Jianqiang; Hua, Xian-Sheng

doi:10.48550/arxiv.2003.03369

Cited by 6 publications

(8 citation statements)

References 101 publications

(133 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…u∈U m =m (max(0, cos(p mu , p m u ))) 2 (10) in which cos(•) means cosine similarity (i.e., the inner product of the two normalized vectors) and the term 2/|U |M (M − 1) is added to calculate the mean.…”

Section: Loss Function and Multi-task Learningmentioning

confidence: 99%

“…The results of the comparison of different methods on both two datasets are shown in Table II. We investigate the Top−N performance with N setting to [10,50,100,200]. From the results, the following observations can be made:…”

Section: E Overall Performance Comparison (Rq1)mentioning

confidence: 99%

“…Deep learning has achieved much success in the field of computer vision and natural language processing [8]- [10]. There are also some attempts on deep learning in the field of recommender systems [11]- [16].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ARGO: Modeling Heterogeneity in E-commerce Recommendation

Wu,

Luo,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Nowadays, E-commerce is increasingly integrated into our daily lives. Meanwhile, shopping process has also changed incrementally from one behavior (purchase) to multiple behaviors (such as view, carting and purchase). Therefore, utilizing interaction data of auxiliary behavior data draws a lot of attention in the E-commerce recommender systems. However, all existing models ignore two kinds of intrinsic heterogeneity which are helpful to capture the difference of user preferences and the difference of item attributes. First (intra-heterogeneity), each user has multiple social identities with otherness, and these different identities can result in quite different interaction preferences. Second (inter-heterogeneity), each item can transfer an item-specific percentage of score from low-level behavior to high-level behavior for the gradual relationship among multiple behaviors. Thus, the lack of consideration of these heterogeneities damages recommendation rank performance. To model the above heterogeneities, we propose a novel method named intrA-and inteR-heteroGeneity recOmmendation model (ARGO). Specifically, we embed each user into multiple vectors representing the user's identities, and the maximum of identity scores indicates the interaction preference. Besides, we regard the item-specific transition percentage as trainable transition probability between different behaviors. Extensive experiments on two real-world datasets show that ARGO performs much better than the stateof-the-art in multi-behavior scenarios.

show abstract

Section: Loss Function and Multi-task Learningmentioning

confidence: 99%

Section: E Overall Performance Comparison (Rq1)mentioning

confidence: 99%

See 1 more Smart Citation

ARGO: Modeling Heterogeneity in E-commerce Recommendation

Wu,

Luo,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning further helped in learning more accurate hashing functions to generate instance codes either in an unsupervised [11,50] or supervised [37,9,51,60] fashion. We refer to [38,61,54] for a more thorough review on deep hashing methods.…”

Section: Related Workmentioning

confidence: 99%

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

Kusupati,

Wallingford,

Ramanujan

et al. 2021

Preprint

View full text Add to dashboard Cite

Learning binary representations of instances and classes is a classical problem with several high potential applications. In modern settings, the compression of high-dimensional neural representations to low-dimensional binary codes is a challenging task and often require large bit-codes to be accurate. In this work, we propose a novel method for Learning Low-dimensional binary Codes (LLC) for instances as well as classes. Our method does not require any side-information, like annotated attributes or label meta-data, and learns extremely low-dimensional binary codes (≈ 20 bits for ImageNet-1K). The learnt codes are super-efficient while still ensuring nearly optimal classification accuracy for ResNet50 on ImageNet-1K. We demonstrate that the learnt codes capture intrinsically important features in the data, by discovering an intuitive taxonomy over classes. We further quantitatively measure the quality of our codes by applying it to the efficient image retrieval as well as out-of-distribution (OOD) detection problems. For ImageNet-100 retrieval problem, our learnt binary codes outperform 16 bit HashNet using only 10 bits and also are as accurate as 10 dimensional real representations. Finally, our learnt binary codes can perform OOD detection, out-of-the-box, as accurately as a baseline that needs ≈ 3000 samples to tune its threshold, while we require none. Code and pre-trained models are available at https://github.com/RAIVNLab/LLC.Preprint. Under review.

show abstract

“…Deep learning-based hashing methods can be divided into supervised hashing and unsupervised hashing [1]. At the early stage, many researchers mainly focused on the supervised hashing methods, which utilize semantic labels to greatly improve the performance of image retrieval [2].…”

Section: Introductionmentioning

confidence: 99%

Deep Unsupervised Hashing by Distilled Smooth Guidance

Luo

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Hashing has been widely used in approximate nearest neighbor search for its storage and computational efficiency. Deep supervised hashing methods are not widely used because of the lack of labeled data, especially when the domain is transferred. Meanwhile, unsupervised deep hashing models can hardly achieve satisfactory performance due to the lack of reliable similarity signals. To tackle this problem, we propose a novel deep unsupervised hashing method, namely Distilled Smooth Guidance (DSG), which can learn a distilled dataset consisting of similarity signals as well as smooth confidence signals. To be specific, we obtain the similarity confidence weights based on the initial noisy similarity signals learned from local structures and construct a priority loss function for smooth similarity-preserving learning. Besides, global information based on clustering is utilized to distill the image pairs by removing contradictory similarity signals. Extensive experiments on three widely used benchmark datasets show that the proposed DSG consistently outperforms the state-of-theart search methods.

show abstract

A Survey on Deep Hashing Methods

Cited by 6 publications

References 101 publications

ARGO: Modeling Heterogeneity in E-commerce Recommendation

ARGO: Modeling Heterogeneity in E-commerce Recommendation

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

Deep Unsupervised Hashing by Distilled Smooth Guidance

Contact Info

Product

Resources

About