Abstract
In computer vision, pre-training models based on large-scale supervised learning have been proven effective over the past few years. However, existing works mostly focus on learning from individual task with single data source (e.g., ImageNet for classification or COCO for detection). This restricted form limits their generalizability and usability due to the lack of vast semantic information from various tasks and data sources. Here, we demonstrate that jointly learning from heterogeneous tasks and multiple data sources contributes to universal visual representation, leading to better transferring results of various downstream tasks. Thus, learning how to bridge the gaps among different tasks and data sources is the key, but it still remains an open question. In this work, we propose a representation learning framework calledX-Learner, which learns the universal feature of multiple vision tasks supervised by various sources, with expansion and squeeze stage:1) Expansion Stage: X-Learner learns the task-specific feature to alleviate task interference and enrich the representation by reconciliation layer.2) Squeeze Stage: X-Learner condenses the model to a reasonable size and learns the universal and generalizable representation for various tasks transferring. Extensive experiments demonstrate that X-Learner achieves strong performance on different tasks without extra annotations, modalities and computational costs compared to existing representation learning methods. Notably, a single X-Learner model shows remarkable gains of 3.0%, 3.3% and 1.8% over current pre-trained models on 12 downstream datasets for classification, object detection and semantic segmentation.
Y. He, G. Huang, S. Chen, J. Teng—Equal contribution.
This is a preview of subscription content,log in via an institution to check access.
Access this chapter
Subscribe and save
- Get 10 units per month
- Download Article/Chapter or eBook
- 1 Unit = 1 Article or 1 Chapter
- Cancel anytime
Buy Now
- Chapter
- JPY 3498
- Price includes VAT (Japan)
- eBook
- JPY 12583
- Price includes VAT (Japan)
- Softcover Book
- JPY 15729
- Price includes VAT (Japan)
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
To avoid ambiguity, we refer to atask as a general vision problem such as classification, detection or segmentation, and asource as a specific dataset or context within a certaintask.
References
Achille, A., Paolini, G., Mbeng, G., Soatto, S.: The information complexity of learning tasks, their structure and their distance. Inf. Inference J. IMA10(1), 51–72 (2021)
Baxter, J.: A model of inductive bias learning. J. Artif. Intell. Res.12, 149–198 (2000)
Ben-David, S., Schuller, R.: Exploiting task relatedness for multiple task learning. In: Schölkopf, B., Warmuth, M.K. (eds.) COLT-Kernel 2003. LNCS (LNAI), vol. 2777, pp. 567–580. Springer, Heidelberg (2003).https://doi.org/10.1007/978-3-540-45167-9_41
Bilen, H., Vedaldi, A.: Universal representations: the missing link between faces, text, planktons, and cat breeds. arXiv preprintarXiv:1701.07275 (2017)
Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 – mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446–461. Springer, Cham (2014).https://doi.org/10.1007/978-3-319-10599-4_29
Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209–1218 (2018)
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprintarXiv:2006.09882 (2020)
Caruana, R.: Multitask learning. Mach. Learn.28(1), 41–75 (1997)
Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprintarXiv:1706.05587 (2017)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607. PMLR (2020)
Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprintarXiv:2003.04297 (2020)
Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750–15758 (2021)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Dosovitskiy, A., Springenberg, J.T., Riedmiller, M., Brox, T.: Discriminative unsupervised feature learning with convolutional neural networks. Adv. Neural. Inf. Process. Syst.27, 766–774 (2014)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision88(2), 303–338 (2010). Jun
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. In: CVPR workshop, pp. 178–178. IEEE (2004)
Fifty, C., Amid, E., Zhao, Z., Yu, T., Anil, R., Finn, C.: Efficiently identifying task groupings for multi-task learning. arXiv preprintarXiv:2109.04617 (2021)
Gao, Y., Ma, J., Zhao, M., Liu, W., Yuille, A.L.: Nddr-CNN: layerwise feature fusing in multi-task CNNs by neural discriminative dimensionality reduction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3205–3214 (2019)
Ghiasi, G., Zoph, B., Cubuk, E.D., Le, Q.V., Lin, T.Y.: Multi-task self-training for learning general representations. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8856–8865 (2021)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the ThirteenthInternational Conference on Artificial Intelligence and Statistic, pp. 249–256. JMLR Workshop and Conference Proceedings (2010)
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.: Bootstrap your own latent: A new approach to self-supervised learning. arXiv preprintarXiv:2006.07733 (2020)
Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Zero-shot detection via vision and language knowledge distillation. arXiv e-prints, pp. arXiv-2104 (2021)
Guo, Y., Li, Y., Wang, L., Rosing, T.: Depthwise convolution is all you need for learning multiple visual domains. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8368–8375 (2019)
Han, H., Jain, A.K., Wang, F., Shan, S., Chen, X.: Heterogeneous face attribute estimation: a deep multi-task learning approach. IEEE Trans. Pattern Anal. Mach. Intell.40(11), 2597–2609 (2017)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729–9738 (2020)
He, K., Girshick, R., Dollár, P.: Rethinking imagenet pre-training. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 4918–4927 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770–778 (2016)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift (2015)
Joulin, A., Van Der Maaten, L., Jabri, A., Vasilache, N.: Learning visual features from large weakly supervised data. In: European Conference on Computer Vision. pp. 67–84. Springer (2016)
Kolesnikov, A., et al.: Big transfer (BiT): general visual representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 491–507. Springer, Cham (2020).https://doi.org/10.1007/978-3-030-58558-7_29
Kornblith, S., Shlens, J., Le, Q.V.: Do better imagenet models transfer better? In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2661–2671 (2019)
Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), Sydney, Australia (2013)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Kumar, A., Daume III, H.: Learning task grouping and overlap in multi-task learning. arXiv preprintarXiv:1206.6417 (2012)
Li, W.-H., Bilen, H.: Knowledge distillation for multi-task learning. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12540, pp. 163–176. Springer, Cham (2020).https://doi.org/10.1007/978-3-030-65414-6_13
Li, Z., Ravichandran, A., Fowlkes, C., Polito, M., Bhotika, R., Soatto, S.: Representation consolidation for training expert students. arXiv preprintarXiv:2107.08039 (2021)
Likhosherstov, V., et al: Polyvit: co-training vision transformers on images, videos and audio. arXiv preprintarXiv:2111.12993 (2021)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014).https://doi.org/10.1007/978-3-319-10602-1_48
Liu, S., Johns, E., Davison, A.J.: End-to-end multi-task learning with attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1871–1880 (2019)
Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 185–201. Springer, Cham (2018).https://doi.org/10.1007/978-3-030-01216-8_12
Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprintarXiv:1306.5151 (2013)
Maninis, K.K., Radosavovic, I., Kokkinos, I.: Attentive single-tasking of multiple tasks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1851–1860 (2019)
Mensink, T., Uijlings, J., Kuznetsova, A., Gygli, M., Ferrari, V.: Factors of influence for transfer learning across diverse appearance domains and task types. arXiv preprintarXiv:2103.13318 (2021)
Misra, I., Shrivastava, A., Gupta, A., Hebert, M.: Cross-stitch networks for multi-task learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3994–4003 (2016)
Nilsback, M.E., Zisserman, A.: A visual vocabulary for flower classification. In: CVPR, vol. 2, pp. 1447–1454. IEEE (2006)
van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprintarXiv:1807.03748 (2018)
Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR, pp. 3498–3505. IEEE (2012)
Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprintarXiv:2103.00020 (2021)
Rebuffi, S.A., Bilen, H., Vedaldi, A.: Learning multiple visual domains with residual adapters. arXiv preprintarXiv:1705.08045 (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst.28, 91–99 (2015)
Ridnik, T., Ben-Baruch, E., Noy, A., Zelnik-Manor, L.: Imagenet-21k pretraining for the masses. arXiv preprintarXiv:2104.10972 (2021)
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: Hints for thin deep nets. arXiv preprintarXiv:1412.6550 (2014)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision115(3), 211–252 (2015)
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. arXiv preprintarXiv:1312.6229 (2013)
Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8430–8439 (2019)
Shen, Z., Liu, Z., Li, J., Jiang, Y.G., Chen, Y., Xue, X.: Object detection from scratch with deep supervision. IEEE Trans. Pattern Anal. Mach. Intell.42(2), 398–412 (2019)
Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746–760. Springer, Heidelberg (2012).https://doi.org/10.1007/978-3-642-33715-4_54
Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 843–852 (2017)
Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: International Conference on Machine Learning, pp. 1139–1147. PMLR (2013)
Van Horn, G., Cole, E., Beery, S., Wilber, K., Belongie, S., Mac Aodha, O.: Benchmarking representation learning for natural world image collections. In: CVPR, pp. 12884–12893 (2021)
Wang, X., Cai, Z., Gao, D., Vasconcelos, N.: Towards universal object detection by domain attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7289–7298 (2019)
Wang, Z., Tsvetkov, Y., Firat, O., Cao, Y.: Gradient vaccine: investigating and improving multi-task optimization in massively multilingual models. arXiv preprintarXiv:2010.05874 (2020)
Xiao, J., Ehinger, K.A., Hays, J., Torralba, A., Oliva, A.: Sun database: exploring a large collection of scene categories. IJCV119(1), 3–22 (2016)
Yalniz, I.Z., Jégou, H., Chen, K., Paluri, M., Mahajan, D.: Billion-scale semi-supervised learning for image classification. arXiv preprintarXiv:1905.00546 (2019)
Yan, X., Misra, I., Gupta, A., Ghadiyaram, D., Mahajan, D.: Clusterfit: improving generalization of visual representations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6509–6518 (2020)
Yang, L., Luo, P., Change Loy, C., Tang, X.: A large-scale car dataset for fine-grained categorization and verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3973–3981 (2015)
Yang, S., Luo, P., Loy, C.C., Tang, X.: Wider face: a face detection benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5525–5533 (2016)
Yang, Y., Eriguchi, A., Muzio, A., Tadepalli, P., Lee, S., Hassan, H.: Improving multilingual translation by representation and gradient regularization. arXiv preprintarXiv:2109.04778 (2021)
Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. arXiv preprintarXiv:2001.06782 (2020)
Zamir, A.R., Sax, A., Cheerla, N., Suri, R., Cao, Z., Malik, J., Guibas, L.J.: Robust learning through cross-task consistency. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11197–11206 (2020)
Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: disentangling task transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3712–3722 (2018)
Zhao, X., Li, H., Shen, X., Liang, X., Wu, Y.: A modulation module for multi-task learning with applications in image retrieval. In: Proceedings of the European Conference on Computer Vision, pp. 401–416 (2018)
Zhao, X., Schulter, S., Sharma, G., Tsai, Y.-H., Chandraker, M., Wu, Y.: Object detection with a unified label space from multiple datasets. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 178–193. Springer, Cham (2020).https://doi.org/10.1007/978-3-030-58568-6_11
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell.40(6), 1452–1464 (2017)
Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vision127(3), 302–321 (2019)
Zhou, X., Koltun, V., Krähenbühl, P.: Simple multi-dataset detection. arXiv preprintarXiv:2102.13086 (2021)
Zhuang, L., Sun, M., Zhou, T., Gao, H., Darrell, T.: Rethinking the value of network pruning (2018)
Zou, D.-N., Zhang, S.-H., Mu, T.-J., Zhang, M.: A new dataset of dog breed images and a benchmark for finegrained classification. Comput. Visual Media6(4), 477–487 (2020).https://doi.org/10.1007/s41095-020-0184-6
Acknowledgements
This work is supported by NTU NAP, MOE AcRF Tier 2 (T2EP20221-0033), and under the RIE2020 Industry Alignment Fund - Industry Collaboration Projects (IAF-ICP) Funding Initiative, as well as cash and in-kind contribution from the industry partner(s) and the Shanghai Committee of Science and Technology (Grant No. 21DZ1100100).
Author information
Authors and Affiliations
Shanghai AI Laboratory, Shanghai, China
Yinan He & Yu Qiao
Sun Yat-sen University, Guangzhou, China
Gengshi Huang
Carnegie Mellon University, Pittsburgh, USA
Siyu Chen
SenseTime Research, Sha Tin, Hong Kong
Jianing Teng, Kun Wang, Zhenfei Yin & Jing Shao
College of Software, Beihang University, Beijing, China
Lu Sheng
S-Lab, Nanyang Technological University, Singapore, Singapore
Ziwei Liu
- Yinan He
You can also search for this author inPubMed Google Scholar
- Gengshi Huang
You can also search for this author inPubMed Google Scholar
- Siyu Chen
You can also search for this author inPubMed Google Scholar
- Jianing Teng
You can also search for this author inPubMed Google Scholar
- Kun Wang
You can also search for this author inPubMed Google Scholar
- Zhenfei Yin
You can also search for this author inPubMed Google Scholar
- Lu Sheng
You can also search for this author inPubMed Google Scholar
- Ziwei Liu
You can also search for this author inPubMed Google Scholar
- Yu Qiao
You can also search for this author inPubMed Google Scholar
- Jing Shao
You can also search for this author inPubMed Google Scholar
Corresponding author
Correspondence toYu Qiao.
Editor information
Editors and Affiliations
Tel Aviv University, Tel Aviv, Israel
Shai Avidan
University College London, London, UK
Gabriel Brostow
Google AI, Accra, Ghana
Moustapha Cissé
University of Catania, Catania, Italy
Giovanni Maria Farinella
Facebook (United States), Menlo Park, CA, USA
Tal Hassner
1Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
He, Y.et al. (2022). X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13686. Springer, Cham. https://doi.org/10.1007/978-3-031-19809-0_29
Download citation
Published:
Publisher Name:Springer, Cham
Print ISBN:978-3-031-19808-3
Online ISBN:978-3-031-19809-0
eBook Packages:Computer ScienceComputer Science (R0)
Share this paper
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative