Dense Contrastive Learning for Self-Supervised Visual Pre-Training
Abstract
To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and pixel-level prediction. To fill this gap, we aim to design an effective, dense self-supervised learning method that directly works at the level of pixels (or local features) by taking into account the correspondence between local features. We present dense contrastive learning (DenseCL), which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images.Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only <1% slower), but demonstrates consistently superior performance when transferring to downstream dense prediction tasks including object detection, semantic segmentation and instance segmentation; and outperforms the state-of-the-art methods by a large margin. Specifically, over the strong MoCo-v2 baseline, our method achieves significant improvements of 2.0% AP on PASCAL VOC object detection, 1.1% AP on COCO object detection, 0.9% AP on COCO instance segmentation, 3.0% mIoU on PASCAL VOC semantic segmentation and 1.8% mIoU on Cityscapes semantic segmentation.Code and models are available at: https://git.io/DenseCL
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?
Pixel-level SSL methods ignore the category-related representation ability required by the LUSS task.
“Despite the good performance for transfer learning, these methods ignore the category-related representation ability required by the LUSS task.”
From Large-Scale Unsupervised Semantic Segmentation (2023) · cites this paper as [95]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · see citing works
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · see citing works
Self-citationYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · see citing works
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460 · see citing works
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · see citing works
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,100 · see citing works
YOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.690 · Cited by 19,892 · see citing works
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 · see citing works
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,268 · see citing works
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 · see citing works
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · see citing works
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857 · see citing works
EfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · cited 1× · see citing works
“Some previous studies have shown the gap between ImageNet pre-training and dense prediction tasks in the context of network architecture [24, 22, 37, 36].”
ResultStructure-from-Motion Revisited
Schonberger, J. L., & Frahm, J.-M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.445 · Cited by 6,433 · see citing works
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 · see citing works
Deep High-Resolution Representation Learning for Human Pose Estimation
Sun, K., Xiao, B., Liu, D., & Wang, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00584 · Cited by 5,984 · see citing works
Context 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 · see citing works
Flownet: Learning optical flow with convolutional networks
Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Smagt, P. V. D., Cremers, D., & Brox, T. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.316 · Cited by 4,313 · see citing works
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. A., Guo, Z. D., Azar, M. G., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.07733 · Cited by 3,846 · see citing works
Unsupervised Feature Learning via Non-parametric Instance Discrimination
Wu, Z., Xiong, Y., Yu, S. X., & Lin, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00393 · Cited by 3,664 · see citing works
Zhang, R., Isola, P., & Efros, A. A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46487-9_40 · Cited by 3,361 · see citing works
Self-citationUnsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
Noroozi, M., & Favaro, P. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_5 · Cited by 2,775 · see citing works
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 · see citing works
Improved Baselines with Momentum Contrastive LearningPreprint
Chen, X., Fan, H., Girshick, R., & He, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.04297 · Cited by 2,579 · see citing works
Unsupervised Representation Learning by Predicting Image Rotations
Gidaris, S., Singh, P., & Komodakis, N. (2018) · arXiv · doi:10.48550/arxiv.1803.07728 · Cited by 2,477 · see citing works
Tian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997 · see citing works
Non-parametric local transforms for computing visual correspondence
Zabih, R., & Woodfill, J. (1994) · Lecture notes in computer science · doi:10.1007/bfb0028345 · Cited by 1,797 · see citing works
Exploring the Limits of Weakly Supervised Pretraining
Mahajan, D., Girshick, R., Ramanathan, V., He, K., Paluri, M., Li, Y., Bharambe, A., & van der Maaten, L. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01216-8_12 · Cited by 1,224 · see citing works
Rethinking ImageNet Pre-Training
He, K., Girshick, R., & Dollár, P. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00502 · Cited by 1,164 · see citing works
A simple framework for contrastive learning of visual representations
Chen, T. (2024) · TIB Data Manager · doi:10.57702/iuuvgtaz · Cited by 1,140 · see citing works
StereoScan: Dense 3d reconstruction in real-time
Geiger, A., Ziegler, J., & Stiller, C. (2011) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2011.5940405 · Cited by 1,092 · see citing works
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
Kong, T., Yao, A., Chen, Y., & Sun, F. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.98 · Cited by 934 · see citing works
Self-citationDense visual SLAM for RGB-D cameras
Kerl, C., Sturm, J., & Cremers, D. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696650 · Cited by 924 · see citing works
Chaitanya, K., Erdil, E., Karani, N., & Konukoglu, E. (2020) · Neural Information Processing Systems · doi:10.3929/ethz-b-000443425 · Cited by 720 · see citing works
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
Xie, S., Gu, J., Guo, D., Qi, C. R., Guibas, L. J., & Litany, O. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58580-8_34 · Cited by 655 · see citing works
Tian, Y., Krishnan, D., & Isola, P. (2019) · arXiv · doi:10.48550/arxiv.1906.05849 · Cited by 465 · see citing works
Scaling and Benchmarking Self-Supervised Visual Representation Learning
Goyal, P., Mahajan, D. K., Gupta, A., & Misra, I. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00649 · Cited by 344 · see citing works
DetNet: Design Backbone for Object Detection
Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y. S., & Sun, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01240-3_21 · Cited by 338 · see citing works
Universal Correspondence NetworkPreprint
Choy, C., Gwak, J., Savarese, S., & Chandraker, M. K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.03558 · Cited by 300 · see citing works
Self-supervised Co-training for Video Representation Learning
Han, T., Xie, W., & Zisserman, A. (2020) · arXiv · doi:10.48550/arxiv.2010.09709 · Cited by 292 · see citing works
Online Deep Clustering for Unsupervised Representation Learning
Zhan, X., Xie, J., Liu, Z., Ong, Y.-S., & Loy, C. C. (2020) · 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/cvpr42600.2020.00672 · Cited by 204 · see citing works
Unsupervised Learning of Dense Shape Correspondence
Halimi, O., Litany, O., Rodolà, E., Bronstein, A. M., & Kimmel, R. (2019) · 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.2019.00450 · Cited by 170 · see citing works
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
Kim, S., Min, D., Ham, B., Jeon, S., Lin, S. C.-F., & Sohn, K. (2017) · 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.2017.73 · Cited by 127 · see citing works
What makes instance discrimination good for transfer learning?
Zhao, N., Wu, Z., Lau, R. W. H., & Lin, S. (2020) · arXiv · doi:10.48550/arxiv.2006.06606 · Cited by 115 · see citing works
PointContrast: Unsupervised Pre-training for 3D Point Cloud UnderstandingPreprint
Xie, S., Gu, J., Guo, D., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.10985 · Cited by 95 · see citing works
An Analysis of Pre-Training on Object DetectionPreprint
Li, H., Singh, B., Najibi, M., Wu, Z., & Davis, L. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.05871 · Cited by 30 · see citing works
Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection
Zhou, D., Zhou, X., Zhang, H., Yi, S., & Ouyang, W. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58598-3_16 · Cited by 18 · see citing works
Unsupervised Feature Learning for Dense Correspondences Across Scenes
Zhang, C., Shen, C., & Shen, T. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0829-6 · Cited by 12 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Exploring Cross-Image Pixel Contrast for Semantic Segmentation
Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., & Gool, L. V. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00721 · Cited by 604 · see citing works
A Cookbook of Self-Supervised Learning
Balestriero, R., Ibrahim, M., Sobal, V., Morcos, A., Shekhar, S., Goldstein, T., Bordes, F., Bardes, A., Mialon, G., Tian, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.12210 · Cited by 182 · see citing works
“It is worth pointing out that some works have only noticed minor increases in performance [Wang et al., 2021a] where it only lead to a 0.3 point performance increase.”
MethodResultInfluentialLeveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
Haliassos, A., Mira, R., Petridis, S., & Pantic, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01453 · Cited by 180 · see citing works
CORE: Consistent Representation Learning for Face Forgery Detection
Ni, Y., Meng, D., Yu, C., Quan, C., Ren, D., & Zhao, Y. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00011 · Cited by 136 · see citing works
Crafting Better Contrastive Views for Siamese Representation Learning
Peng, X., Wang, K., Zhu, Z., Wang, M., & You, Y. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01556 · Cited by 122 · 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
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow
Weinzaepfel, P., Lucas, T., Leroy, V., Cabon, Y., Arora, V., Brégier, R., Csurka, G., Antsfeld, L., Chidlovskii, B., & Revaud, J. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01647 · Cited by 110 · see citing works
Large-Scale Unsupervised Semantic Segmentation
Gao, S., Li, Z.-Y., Yang, M.-H., Cheng, M.-M., Han, J., & Torr, P. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3218275 · Cited by 88 · see citing works
Lin, Z., Zhang, D., Shi, D., Xu, R., Tao, Q., Wu, L., He, M., & Ge, Z. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104281 · Cited by 39 · see citing works
Self-Supervised Learning for Anomaly Detection With Dynamic Local Augmentation
Yoa, S., Lee, S., Kim, C., & Kim, H. J. (2021) · IEEE Access · doi:10.1109/access.2021.3124525 · Cited by 38 · see citing works
VideoMAC: Video Masked Autoencoders Meet ConvNets
Pei, G., Chen, T., Jiang, X., Liu, H., Sun, Z., & Yao, Y. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02145 · Cited by 23 · see citing works
What Do Self-Supervised Vision Transformers Learn?
Park, N., Kim, W., Heo, B., Kim, T., & Yun, S. (2023) · arXiv · doi:10.48550/arxiv.2305.00729 · Cited by 29 · see citing works
“For example, Zhou et al. (2022); Wang et al. (2021); Yu et al. (2022) achieve high predictive performance by harmonizing the image-level and the token-level self-supervised learning.”
Background
- Authors
- Wang, X., Zhang, R., Shen, C., Kong, T., & Li, L.
- Affiliations
- The University of Adelaide (AU)
- Tongji University (CN)
- ByteDance (China) (CN)
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 3023-3032
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3168822201
- Semantic Scholar
- 6f92dcefc5f6b4346f619ae7546a8bd2d6decade
- Cited by
- 660
- References
- 49
- Citations by year
- 2026: 48 · 2025: 126 · 2024: 130 · 2023: 188 · 2022: 132 · 2021: 34 · 2020: 2
- FWCI
- 55.80
- Type
- conference paper
- Language
- en
- Open access
- closed
- 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)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- dense prediction, object detection, semantic segmentation, instance segmentation, MoCo v2
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
