The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Interpolation-based Semi-supervised Learning for Object Detection
Open accessAbstract
Despite the data labeling cost for the object detection tasks being substantially more than that of the classification tasks, semi-supervised learning methods for object detection have not been studied much. In this paper, we propose an Interpolation-based Semi-supervised learning method for object Detection (ISD), which considers and solves the problems caused by applying conventional Interpolation Regularization (IR) directly to object detection. We divide the output of the model into two types according to the objectness scores of both original patches that are mixed in IR. Then, we apply a separate loss suitable for each type in an unsupervised manner. The proposed losses dramatically improve the performance of semi-supervised learning as well as supervised learning. In the supervised learning setting, our method improves the baseline methods by a significant margin. In the semi-supervised learning setting, our algorithm improves the performance on a benchmark dataset (PASCAL VOC and MSCOCO) in a benchmark architecture (SSD). Our code is available at https://github.com/soo89/ISD-SSD
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Soft Proposal Networks for Weakly Supervised Object Localization
Zhu, Y., Zhou, Y., Ye, Q., Qiu, Q., & Jiao, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.204 · Cited by 156
Flagged first, then by citations
Research works printed but not linked: 26
- zhang, 2018, mixup: Beyond empirical risk minimization, International Conference on Learning Representations
- 10.1109/ICCV.2019.00612 · DOI · Paper page
- 10.1007/s11263-009-0275-4 · DOI · Paper page
- jeong, 2019, Consistency-based semi-supervised learning for object detection, Advances in neural information processing systems, 10758
- 10.1109/CVPR.2017.457 · DOI
- lin, 2014, Microsoft coco: Common objects in context, European Conference on Computer Vision, 740
- liu, 2016, Ssd: Single shot multibox detector, European Conference on Computer Vision, 21
- miyato, 2018, Virtual adversarial training: a regularization method for supervised and semi-supervised learning, IEEE Transactions on Pattern Analysis and Machine Intelligence
- 10.5220/0007345602890296 · DOI
- 10.1109/CVPR.2015.7298824 · DOI
- 10.24963/ijcai.2018/135 · DOI
- berthelot, 2019, Mixmatch: A holistic approach to semi-supervised learning, Advances in neural information processing systems, 5050
- verma, 2019, Graphmix: Regularized training of graph neural networks for semi-supervised learning, ArXiv, abs 1909 11715
- berthelot, 2020, Remixmatch: Semi-supervised learning with distribution matching and augmentation anchoring, International Conference on Learning Representations
- 10.1109/CVPR.2018.00173 · DOI · Paper page
- berthelot, 2019, Understanding and improving interpolation in autoencoders via an adversarial regularizer, International Conference on Learning Representations
- devries, 2017, Improved regularization of convolutional neural networks with cutout, CoRR, abs 1708 4552
- beckham, 2019, On adversarial mixup resynthesis, Advances in neural information processing systems, 4348
- 10.1109/TPAMI.2011.155 · DOI
- 10.1007/978-3-319-46478-7_34 · DOI
- 10.1109/ICCV.2017.366 · DOI
- 10.1109/CVPR.2016.233 · DOI
- 10.1109/CVPR.2018.00575 · DOI
- tarvainen, 2017, Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results, Advances in neural information processing systems, 1195
- 10.24963/ijcai.2019/504 · DOI
- verma, 2019, Proceedings of the 36th International Conference on Machine Learning volume 97 of Proceedings of Machine Learning Research, 6438
Cited by
Sorted by citations
Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection
Elezi, I., Yu, Z., Anandkumar, A., Leal-Taixe, L., & Alvarez, J. M. (2021) · arXiv · Cited by 50
“While going from semi-supervised image classification to semi-supervised object detection is challenging, some promising directions are given in recent works [3, 36, 37]”
Background
Metadata
- Authors
- Jeong, J., Verma, V., Hyun, M., Kannala, J., & Kwak, N.
- Affiliations
- Seoul National University (KR)
- Mila - Quebec Artificial Intelligence Institute (CA)
- SK Group (United States) (US)
- Aalto University (FI)
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 11597-11606
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3179069071
- Cited by
- 66
- References
- 1
- Citations by year
- 2026: 5 · 2025: 5 · 2024: 13 · 2023: 15 · 2022: 21 · 2021: 6
- FWCI
- 4.50
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Seoul National University Open Repository (Seoul National University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Research Foundation of Korea
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- semi-supervised object detection, data labeling cost, SSD, Pascal VOC, MS COCO
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
