Semi-Supervised Self-Training of Object Detection Models
Abstract
The construction of appearance-based object detection systems is time-consuming and difficult because a large number of training examples must be collected and manually labeled in order to capture variations in object appearance. Semi-supervised training is a means for reducing the effort needed to prepare the training set by training the model with a small number of fully labeled examples and an additional set of unlabeled or weakly labeled examples. In this work we present a semi-supervised approach to training object detection systems based on self-training. We implement our approach as a wrapper around the training process of an existing object detector and present empirical results. The key contributions of this empirical study is to demonstrate that a model trained in this manner can achieve results comparable to a model trained in the traditional manner using a much larger set of fully labeled data, and that a training data selection metric that is defined independently of the detector greatly outperforms a selection metric based on the detection confidence generated by the detector.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The simple ConvNeXt segmentation head outperforms Segmenter on average slightly better on semantic segmentation.
“We find that this simple ConvNeXt head outperforms Segmenter, as shown in Table 7.”
From MultiMAE: Multi-modal Multi-task Masked Autoencoders (2022) · cites this paper as [53]
Cites
Neural Networks for Pattern Recognition
Bishop, C. M. (1995) · doi:10.1093/oso/9780198538493.001.0001 · Cited by 12,287 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
He, H., & Garcia, E. A. (2009) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2008.239 · Cited by 10,359 · see citing works
A survey on semi-supervised learning
van Engelen, J. E., & Hoos, H. H. (2020) · Machine Learning · doi:10.1007/s10994-019-05855-6 · Cited by 2,666 · see citing works
Unsupervised Domain Adaptation of Object Detectors: A Survey
Oza, P., Sindagi, V. A., VS, V., & Patel, V. M. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3217046 · Cited by 313 · see citing works
MultiMAE: Multi-modal Multi-task Masked Autoencoders
Bachmann, R., Mizrahi, D., Atanov, A., & Zamir, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19836-6_20 · Cited by 268 · see citing works
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
Chen, L.-C., Lopes, R. G., Cheng, B., Collins, M. D., Cubuk, E. D., Zoph, B., Adam, H., & Shlens, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58545-7_40 · Cited by 165 · see citing works
Denoising Pretraining for Semantic Segmentation
Brempong, E. A., Kornblith, S., Chen, T., Parmar, N., Minderer, M., & Norouzi, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00462 · Cited by 120 · see citing works
Cloud-based scalable object detection and classification in video streams
Yaseen, M. U., Anjum, A., Rana, O., & Hill, R. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2017.02.003 · Cited by 55 · see citing works
Training Object Detectors With Noisy Data
Chadwick, S., & Newman, P. (2019) · 2019 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2019.8814137 · Cited by 46 · see citing works
Yang, Z., Feng, Z., Huo, R., Lin, H., Zheng, H., Nie, R., & Chen, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126694 · Cited by 17 · see citing works
Hailat, Z., Komarichev, A., & Chen, X.-W. (2018) · 2018 24th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr.2018.8546327 · Cited by 13 · see citing works
- Authors
- Rosenberg, C., Hebert, M., & Schneiderman, H.
- Affiliations
- Google (United States) (US)
- Carnegie Mellon University (US)
- Venue
- 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1
- Publisher
- IEEE
- Published
- 2005-01
- Pages
- 29-36
- ISSN
- 2472-6737 (ISSN-L)
- OpenAlex
- W2079057609
- Cited by
- 796
- References
- 1
- Citations by year
- 2026: 14 · 2025: 41 · 2024: 48 · 2023: 69 · 2022: 72 · 2021: 81 · 2020: 79 · 2019: 64 · 2018: 49 · 2017: 34 · 2016: 35 · 2015: 29 · 2014: 29 · 2013: 30 · 2012: 27
- FWCI
- 9.09
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Winter Conference on Applications of Computer Vision (publishedVersion)
- 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 learning, self-training, object detection, weakly labeled data, unlabeled data, training data selection, detection confidence
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
