The DOI matches its Crossref record; 57 of the 58 references it cites were found in a registry or an index.
Unsupervised Learning of Visual Representations Using Videos
Open accessAbstract
Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)? In this paper, we present a simple yet surprisingly powerful approach for unsupervised learning of CNN. Specifically, we use hundreds of thousands of unlabeled videos from the web to learn visual representations. Our key idea is that visual tracking provides the supervision. That is, two patches connected by a track should have similar visual representation in deep feature space since they probably belong to same object or object part. We design a Siamese-triplet network with a ranking loss function to train this CNN representation. Without using a single image from ImageNet, just using 100K unlabeled videos and the VOC 2012 dataset, we train an ensemble of unsupervised networks that achieves 52% mAP (no bounding box regression). This performance comes tantalizingly close to its ImageNet-supervised counterpart, an ensemble which achieves a mAP of 54.4%. We also show that our unsupervised network can perform competitively in other tasks such as surface-normal estimation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“Our survey found that most deepfake detection methods assume a static game (Mirsky and Lee 2021; Wang and Gupta 2015).”
From Deepfake video detection: challenges and opportunities (2024) · cites this paper as Wang and Gupta 2015
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
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436
Indoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760
High-Speed Tracking with Kernelized Correlation Filters
Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2345390 · Cited by 5,753
Dimensionality Reduction by Learning an Invariant Mapping
Hadsell, R., Chopra, S., & LeCun, Y. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.100 · Cited by 5,336
Greedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841
Learning a Similarity Metric Discriminatively, with Application to Face Verification
Chopra, S., Hadsell, R., & LeCun, Y. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.202 · Cited by 4,036
(1989) · neural information processing systems · Cited by 3,736
Sparse coding with an overcomplete basis set: A strategy employed by V1?
Olshausen, B. A., & Field, D. J. (1997) · Vision Research · doi:10.1016/s0042-6989(97)00169-7 · Cited by 3,642
Action Recognition with Improved Trajectories
Wang, H., & Schmid, C. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.441 · Cited by 3,407
Unsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629
Self-citationLee, H., Grosse, R., Ranganath, R., & Ng, A. Y. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553453 · Cited by 2,412
Deep Metric Learning Using Triplet Network
Hoffer, E., & Ailon, N. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-24261-3_7 · Cited by 2,134
Unsupervised Learning of Video Representations using LSTMs
Srivastava, N., Mansimov, E., & Salakhutdinov, R. (2015) · arXiv · doi:10.48550/arxiv.1502.04681 · Cited by 1,861
Building high-level features using large scale unsupervised learning
Le, Q. V. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639343 · Cited by 1,695
Quattoni, A., & Torralba, A. B. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2009.5206537 · Cited by 1,533
Slow Feature Analysis: Unsupervised Learning of Invariances
Wiskott, L., & B, T. J. S. A. (2002) · Neural Computation · doi:10.1162/089976602317318938 · Cited by 1,358
Learning Fine-Grained Image Similarity with Deep Ranking
Wang, J., Song, Y., Leung, T., Rosenberg, C., Wang, J., Philbin, J. F., Chen, B., & Wu, Y. N. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.180 · Cited by 1,317
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
Ranzato, M., Huang, F. J., Boureau, Y.-L., & LeCun, Y. (2007) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2007.383157 · Cited by 1,130
The "Wake-Sleep" Algorithm for Unsupervised Neural Networks
Hinton, G. E., Dayan, P., Frey, B. J., & Neal, R. M. (1995) · Science · doi:10.1126/science.7761831 · Cited by 1,070
Multimodal Learning with Deep Boltzmann Machines
Srivastava, N., & Salakhutdinov, R. (2012) · doi:10.5555/2627435.2697059 · Cited by 1,070
Le, Q. V., Zou, W. Y., Yeung, S. Y., & Ng, A. Y. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995496 · Cited by 975
Discovering objects and their location in images
Šivic, J., Russell, B. C., Efros, A. A., Zisserman, A., & Freeman, W. T. (2005) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2005.77 · Cited by 973
Pedestrian Detection with Unsupervised Multi-stage Feature Learning
Sermanet, P., Kavukcuoglu, K., Chintala, S., & LeCun, Y. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.465 · Cited by 762
Learning invariance from transformation sequences
Földiák, P. (1991) · Neural Computation · doi:10.1162/neco.1991.3.2.194 · Cited by 661 · cited 1×
“Therefore, researchers have started focusing on learning feature representations using videos [11, 53, 27, 43, 56, 16, 48, 34, 45].”
BackgroundConvolutional Learning of Spatio-temporal Features
Taylor, G. W., Fergus, R., LeCun, Y., & Bregler, C. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15567-3_11 · Cited by 652
Building high-level features using large scale unsupervised learning
Ranzato, M., Monga, R., Devin, M., Chen, K., Corrado, G. S., Dean, J., Le, Q. V., & Ng, A. Y. (2012) · International Conference on Machine Learning · Cited by 646
Using Multiple Segmentations to Discover Objects and their Extent in Image Collections
Russell, B. C., Freeman, W. T., Efros, A. A., Šivic, J., & Zisserman, A. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.326 · Cited by 618
Unsupervised Discovery of Mid-Level Discriminative Patches
Singh, S., Gupta, A., & Efros, A. A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33709-3_6 · Cited by 517
Self-citationZhang, R., Lin, L., Zhang, R., Zuo, W., & Lei Zhang, A. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2467315 · Cited by 504
Learning descriptors for object recognition and 3D pose estimation
Wohlhart, P., & Lepetit, V. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298930 · Cited by 458
Designing deep networks for surface normal estimation
Wang, X., Fouhey, D. F., & Gupta, A. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298652 · Cited by 348
Self-citationDeep learning from temporal coherence in video
Mobahi, H., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553469 · Cited by 328
Discriminative Decorrelation for Clustering and Classification
Hariharan, B., Malik, J., & Ramanan, D. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33765-9_33 · Cited by 274
Deep Convolutional Ranking for Multilabel Image AnnotationPreprint
Gong, Y., Jia, Y., Leung, T., Toshev, A., & Ioffe, S. (2014) · Cited by 272
Mid-level Visual Element Discovery as Discriminative Mode Seeking
Doersch, C., Gupta, A., & Efros, A. A. (2013) · neural information processing systems · Cited by 238
Self-citationHierarchical face parsing via deep learning
Luo, P., Wang, X., & Tang, X. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247963 · Cited by 190
Self-citationRobust Boltzmann Machines for recognition and denoising
Tang, Y., Salakhutdinov, R., & Hinton, G. E. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247936 · Cited by 173
Data-Driven 3D Primitives for Single Image Understanding
Fouhey, D. F., Gupta, A., & Hebert, M. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.421 · Cited by 167
Self-citationUnsupervised Learning of Spatiotemporally Coherent Metrics
Goroshin, R., Bruna, J., Tompson, J., Eigen, D., & LeCun, Y. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.465 · Cited by 163
Matching-CNN meets KNN: Quasi-parametric human parsing
Liu, S., Liang, X., Liu, L., Shen, X., Yang, J., Xu, C., Lin, L., Cao, X., & Yan, S. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298748 · Cited by 142
Deep Learning of Invariant Features via Simulated Fixations in Video
Zou, W. Y., Shenghuo Zhu, B., Yu, K., & Ng, A. Y. (2012) · Cited by 130
Describing Visual Scenes using Transformed Dirichlet Processes
Torralba, A. B., Willsky, A. S., Sudderth, E. B., & Freeman, W. T. (2005) · neural information processing systems · Cited by 122
Discriminatively Trained Dense Surface Normal Estimation
Ladický, Ľ., Zeisl, B., & Pollefeys, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10602-1_31 · Cited by 120
Unfolding an Indoor Origami World
Fouhey, D. F., Gupta, A., & Hebert, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10599-4_44 · Cited by 85
Self-citationThe Shape Boltzmann Machine: A strong model of object shape
Eslami, S. M. A., Heess, N., & Winn, J. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247702 · Cited by 61
Context as Supervisory Signal: Discovering Objects with Predictable Context
Doersch, C., Gupta, A., & Efros, A. A. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10578-9_24 · Cited by 39
Self-citationUnsupervised learning of invariant features using video
Stavens, D., & Thrun, S. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5539773 · Cited by 36
Computational Baby LearningPreprint
Liang, X., Liu, S., Wei, Y., Liu, L., Lin, L., & Yan, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.2861 · Cited by 17
Research works printed but not linked: 1
- lecun, 1990, Handwritten digit recognition with a backpropagation network, NIPS
Cited by
Sorted by citations
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
“In Computer Vision [28] use a triplet loss on tracked video patches so that patches from the same object at different timesteps are more similar to each other than to random patches.”
BackgroundMethodContext Encoders: Feature Learning by Inpainting
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., & Efros, A. A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.278 · Cited by 5,691
Metadata
- Authors
- Wang, X., & Gupta, A.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- 2015 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2015-12
- Pages
- 2794-2802
- OpenAlex
- W219040644
- Cited by
- 1,005
- References
- 58
- Citations by year
- 2026: 8 · 2025: 32 · 2024: 44 · 2023: 63 · 2022: 97 · 2021: 146 · 2020: 173 · 2019: 140 · 2018: 121 · 2017: 108 · 2016: 65 · 2015: 8
- FWCI
- 41.29
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1320083)
- Nvidia
- Defense Advanced Research Projects Agency (FA8750-14- 2-0244, FA8750)
- Multidisciplinary University Research Initiative
- Office of Naval Research (N00014-10-10934, MURI N000141010934)
- 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 › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- video-based learning, visual object tracking, ranking loss, object detection, unlabeled video, surface normal estimation, convolutional neural networks
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
