Stochastic Class-Based Hard Example Mining for Deep Metric Learning
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
Performance of deep metric learning depends heavily on the capability of mining hard negative examples during training. However, many metric learning algorithms often require intractable computational cost due to frequent feature computations and nearest neighbor searches in a large-scale dataset. As a result, existing approaches often suffer from trade-off between training speed and prediction accuracy. To alleviate this limitation, we propose a stochastic hard negative mining method. Our key idea is to adopt class signatures that keep track of feature embedding online with minor additional cost during training, and identify hard negative example candidates using the signatures. Given an anchor instance, our algorithm first selects a few hard negative classes based on the class-to-sample distances and then performs a refined search in an instance-level only from the selected classes. As most of the classes are discarded at the first step, it is much more efficient than exhaustive search while effectively mining a large number of hard examples. Our experiment shows that the proposed technique improves image retrieval accuracy substantially; it achieves the state-of-the-art performance on the several standard benchmark datasets.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
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 · cited 6×
“To reduce the computational overhead to identify hard examples, existing works have explored two directions: an exact search within each minibatch [20, 7, 19] and an approximate search from the whole dataset.”
BackgroundInfluentialA Discriminative Feature Learning Approach for Deep Face Recognition
Wen, Y., Zhang, K., Li, Z., & Qiao, Y. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_31 · Cited by 4,077 · cited 1×
“[34] are related to ours in a sense that class representatives are jointly trained with the feature extractor.”
BackgroundFeatures for Multi-target Multi-camera Tracking and Re-identification
Ristani, E., & Tomasi, C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00632 · Cited by 556
Cited by
A Metric Learning Reality Check
Musgrave, K., Belongie, S., & Lim, S.-N. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58595-2_41 · Cited by 414
Cross-Batch Memory for Embedding Learning
Wang, X., Zhang, H., Huang, W., & Scott, M. R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00642 · Cited by 254
Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection
Luo, A., Kong, C., Huang, J., Hu, Y., Kang, X., & Kot, A. C. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3332218 · Cited by 115
Text Transformations in Contrastive Self-Supervised Learning: A Review
Bhattacharjee, A., Karami, M., & Liu, H. (2022) · Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/757 · Cited by 20
AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
Wang, D., Li, M., Gong, C., & Chandra, V. (2020) · arXiv · doi:10.48550/arxiv.2011.09011 · Cited by 10
Metadata
- Authors
- Suh, Y., Han, B., Kim, W., & Lee, K. M.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Volume
- 2019
- Pages
- 7244-7252
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2948638722
- Cited by
- 133
- References
- 4
- FWCI
- 6.16
- Type
- conference paper
- Language
- en
- Open access
- closed
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
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.