Unsupervised Learning from Video to Detect Foreground Objects in Single Images
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Unsupervised learning from visual data is one of the most difficult challenges in computer vision. It is essential for understanding how visual recognition works. Learning from unsupervised input has an immense practical value, as huge quantities of unlabeled videos can be collected at low cost. Here we address the task of unsupervised learning to detect and segment foreground objects in single images. We achieve our goal by training a student pathway, consisting of a deep neural network that learns to predict, from a single input image, the output of a teacher pathway that performs unsupervised object discovery in video. Our approach is different from the published methods that perform unsupervised discovery in videos or in collections of images at test time. We move the unsupervised discovery phase during the training stage, while at test time we apply the standard feed-forward processing along the student pathway. This has a dual benefit: firstly, it allows, in principle, unlimited generalization possibilities during training, while remaining fast at testing. Secondly, the student not only becomes able to detect in single images significantly better than its unsupervised video discovery teacher, but it also achieves state of the art results on two current benchmarks, YouTube Objects and Object Discovery datasets. At test time, our system is two orders of magnitude faster than other previous methods.
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
GrabCut: Interactive foreground extraction using iterated graph cuts
Rother, C., Kolmogorov, V., & Blake, A. (2004) · ACM Transactions on Graphics · doi:10.1145/1015706.1015720 · Cited by 5,703
Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification
Misra, I., Zitnick, C. L., & Hebert, M. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_32 · Cited by 779 · cited 2×
“Many recent unsupervised methods in vision follow two main directions: one is to learn powerful features in a completely unsupervised manner and then use them in a classic supervised learning scheme in combination with different classifiers, such as SVMs or CNNs [30, 24, 22].”
Method
Cited by
Object Detection With Deep Learning: A Review
Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2876865 · Cited by 5,545
“To release this burden, semantic prior [55], unsupervised object discovery [221], multiple instance learning [222] and deep neural network prediction [47] can be integrated to make best use of image-level supervision to”
MethodSelf-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
Jing, L., & Tian, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2992393 · Cited by 2,036
A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPT
Zhou, C., Li, Q., Li, C., Yu, J., Liu, Y., Wang, G., Zhang, K., Ji, C., Yan, Q., He, L., et al. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02443-6 · Cited by 557
A Survey on Self-Supervised Learning: Algorithms, Applications, and Future Trends
Gui, J., Chen, T., Zhang, J., Cao, Q., Sun, Z., Luo, H., & Tao, D. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3415112 · Cited by 552
Mixed supervision for surface-defect detection: From weakly to fully supervised learning
Božič, J., Tabernik, D., & Skočaj, D. (2021) · Computers in Industry · doi:10.1016/j.compind.2021.103459 · Cited by 377
Metadata
- Authors
- Croitoru, I., Bogolin, S.-V., & Leordeanu, M.
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 4345-4353
- OpenAlex
- W2604474734
- Cited by
- 53
- References
- 3
- FWCI
- 2.10
- Type
- conference paper
- 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
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.