Improved Deep Hashing With Soft Pairwise Similarity for Multi-Label Image Retrieval
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Recently, many deep hashing methods have been proposed and shown largely improved performance over traditional feature-learning methods. Most of these methods examine the pairwise similarity on the semantic-level labels, where the pairwise similarity is generally defined in a hard-assignment way. That is, the pairwise similarity is “1” if they share no less than one class label and “0” if they do not share any. However, such similarity definition cannot reflect the similarity ranking for pairwise images that hold multiple labels. In this paper, an improved deep hashing method is proposed to enhance the ability of multi-label image retrieval. We introduce a pairwise quantified similarity calculated on the normalized semantic labels. Based on this, we divide the pairwise similarity into two situations-“hard similarity” and “soft similarity,” where cross-entropy loss and mean square error loss are adapted respectively for more robust feature learning and hash coding. Experiments on four popular datasets demonstrate that the proposed method outperforms the competing methods and achieves the state-of-the-art performance in multi-label image retrieval.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408
Cumulated gain-based evaluation of IR techniques
Järvelin, K., & Kekäläinen, J. (2002) · ACM Transactions on Information Systems · doi:10.1145/582415.582418 · Cited by 4,841 · cited 8×
“(16) 1Codes are available at https://sites.google.com/site/qinzoucn/ Then, the normalized DCG (NDCG) score at the position n can be calculated by NDCG@n = DCG@nZn , where Zn is the maximum value of DCG@n, which constrains the value of NDCG in the range [0, 1].”
MethodInfluentialNUS-WIDE: a real-world web image database from National University of Singapore
Chua, T.-S., Tang, J., Hong, R., Li, H., Luo, Z., & Zheng, Y. (2009) · Proceedings of the ACM International Conference on Image and Video Retrieval · doi:10.1145/1646396.1646452 · Cited by 3,025 · cited 9×
“Although IDHN-fine-ce has achieved outstanding performance on VOC2102 dataset, it does not show advantage on other two datasets – NUS-WIDE and Flickr, while there are complicated and abundant semantic relation on these two image datasets than VOC2012.”
BackgroundInfluentialDeep Learning Face Representation by Joint Identification-Verification
Sun, Y., Wang, X., & Tang, X. (2014) · arXiv · doi:10.48550/arxiv.1406.4773 · Cited by 1,906
Deep Supervised Hashing for Fast Image Retrieval
Liu, H., Wang, R., Shan, S., & Chen, X. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.227 · Cited by 933
HashNet: Deep Learning to Hash by Continuation
Cao, Z., Long, M., Wang, J., & Yu, P. S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.598 · Cited by 777 · cited 12×
“The top-20 results of DHN, DMSSPH and DLBHC have incorrect retrieval results, and the top-20 results of DQN and HashNet include some low similarity results, as denoted by the blue-box images.”
MethodInfluentialDeep Hashing Network for Efficient Similarity Retrieval
Zhu, H., Long, M., Wang, J., & Cao, Y. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10235 · Cited by 664 · cited 4×
“We compare our method with several state-of-the-art hashing methods, including three unsupervised methods LSH [37], SH [3] and ITQ [8], and two traditional supervised methods MLH [6], KSH [7], and one classification-based deep hashing methods DLBHC [46], three deep hashing methods with coarse pairwise similarity defin…”
MethodInfluential
Cited by
Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks
Zou, Q., Jiang, H., Dai, Q., Yue, Y., Chen, L., & Wang, Q. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2949603 · Cited by 358
Self-citationDeep Learning-Based Gait Recognition Using Smartphones in the Wild
Zou, Q., Wang, Y., Wang, Q., Zhao, Y., & Li, Q. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.2985628 · Cited by 305
Self-citationDeep Learning-Based Gait Recognition Using Smartphones in the Wild
Zou, Q., Wang, Y., Wang, Q., Zhao, Y., & Li, Q. (2018) · arXiv · doi:10.48550/arxiv.1811.00338 · Cited by 305
Self-citation
Metadata
- Authors
- Zhang, Z., Zou, Q., Lin, Y., Chen, L., & Wang, S.
- Venue
- IEEE Transactions on Multimedia
- Published
- 2020-02
- Volume
- 22
- Issue
- 2
- Pages
- 540-553
- ISSN
- 1520-9210 (ISSN-L)
- 1941-0077
- OpenAlex
- W2966218308
- Cited by
- 195
- References
- 9
- FWCI
- 8.60
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Improved Deep Hashing With Soft Pairwise Similarity for Multi-Label Image Retrieval. https://app.cochat.ai/papers/10.1109/tmm.2019.2929957
- The paper
- Zhang, Z., Zou, Q., Lin, Y., Chen, L., & Wang, S. (2020). Improved Deep Hashing With Soft Pairwise Similarity for Multi-Label Image Retrieval. IEEE Transactions on Multimedia. https://doi.org/10.1109/tmm.2019.2929957
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.