Skip to main content

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13686))

Included in the following conference series:

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 called X-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

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    To avoid ambiguity, we refer to a task as a general vision problem such as classification, detection or segmentation, and a source as a specific dataset or context within a certain task.

References

  1. Achille, A., Paolini, G., Mbeng, G., Soatto, S.: The information complexity of learning tasks, their structure and their distance. Inf. Inference J. IMA 10(1), 51–72 (2021)

    MathSciNet  MATH  Google Scholar 

  2. Baxter, J.: A model of inductive bias learning. J. Artif. Intell. Res. 12, 149–198 (2000)

    Article  MathSciNet  MATH  Google Scholar 

  3. 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

    Chapter  MATH  Google Scholar 

  4. Bilen, H., Vedaldi, A.: Universal representations: the missing link between faces, text, planktons, and cat breeds. arXiv preprint arXiv:1701.07275 (2017)

  5. 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

    Chapter  Google Scholar 

  6. 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)

    Google Scholar 

  7. Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprint arXiv:2006.09882 (2020)

  8. Caruana, R.: Multitask learning. Mach. Learn. 28(1), 41–75 (1997)

    Article  MathSciNet  Google Scholar 

  9. Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)

  10. 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)

    Google Scholar 

  11. Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)

  12. 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)

    Google Scholar 

  13. 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)

    Google Scholar 

  14. 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)

    Google Scholar 

  15. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303–338 (2010). Jun

    Article  Google Scholar 

  16. 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)

    Google Scholar 

  17. Fifty, C., Amid, E., Zhao, Z., Yu, T., Anil, R., Finn, C.: Efficiently identifying task groupings for multi-task learning. arXiv preprint arXiv:2109.04617 (2021)

  18. 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)

    Google Scholar 

  19. 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)

    Google Scholar 

  20. 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)

    Google Scholar 

  21. 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 preprint arXiv:2006.07733 (2020)

  22. 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)

    Google Scholar 

  23. 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)

    Google Scholar 

  24. 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)

    Article  Google Scholar 

  25. 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)

    Google Scholar 

  26. 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)

    Google Scholar 

  27. 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)

    Google Scholar 

  28. Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift (2015)

    Google Scholar 

  29. 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)

    Google Scholar 

  30. 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

    Chapter  Google Scholar 

  31. 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)

    Google Scholar 

  32. 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)

    Google Scholar 

  33. Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)

    Google Scholar 

  34. Kumar, A., Daume III, H.: Learning task grouping and overlap in multi-task learning. arXiv preprint arXiv:1206.6417 (2012)

  35. 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

    Chapter  Google Scholar 

  36. Li, Z., Ravichandran, A., Fowlkes, C., Polito, M., Bhotika, R., Soatto, S.: Representation consolidation for training expert students. arXiv preprint arXiv:2107.08039 (2021)

  37. Likhosherstov, V., et al: Polyvit: co-training vision transformers on images, videos and audio. arXiv preprint arXiv:2111.12993 (2021)

  38. 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)

    Google Scholar 

  39. 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

    Chapter  Google Scholar 

  40. 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)

    Google Scholar 

  41. 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

    Chapter  Google Scholar 

  42. Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)

  43. 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)

    Google Scholar 

  44. Mensink, T., Uijlings, J., Kuznetsova, A., Gygli, M., Ferrari, V.: Factors of influence for transfer learning across diverse appearance domains and task types. arXiv preprint arXiv:2103.13318 (2021)

  45. 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)

    Google Scholar 

  46. Nilsback, M.E., Zisserman, A.: A visual vocabulary for flower classification. In: CVPR, vol. 2, pp. 1447–1454. IEEE (2006)

    Google Scholar 

  47. van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)

  48. Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR, pp. 3498–3505. IEEE (2012)

    Google Scholar 

  49. Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)

  50. Rebuffi, S.A., Bilen, H., Vedaldi, A.: Learning multiple visual domains with residual adapters. arXiv preprint arXiv:1705.08045 (2017)

  51. 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)

    Google Scholar 

  52. Ridnik, T., Ben-Baruch, E., Noy, A., Zelnik-Manor, L.: Imagenet-21k pretraining for the masses. arXiv preprint arXiv:2104.10972 (2021)

  53. Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)

  54. Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)

    Article  MathSciNet  Google Scholar 

  55. Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)

  56. 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)

    Google Scholar 

  57. 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)

    Article  Google Scholar 

  58. 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

    Chapter  Google Scholar 

  59. 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)

    Google Scholar 

  60. 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)

    Google Scholar 

  61. 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)

    Google Scholar 

  62. 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)

    Google Scholar 

  63. Wang, Z., Tsvetkov, Y., Firat, O., Cao, Y.: Gradient vaccine: investigating and improving multi-task optimization in massively multilingual models. arXiv preprint arXiv:2010.05874 (2020)

  64. Xiao, J., Ehinger, K.A., Hays, J., Torralba, A., Oliva, A.: Sun database: exploring a large collection of scene categories. IJCV 119(1), 3–22 (2016)

    Article  MathSciNet  Google Scholar 

  65. Yalniz, I.Z., Jégou, H., Chen, K., Paluri, M., Mahajan, D.: Billion-scale semi-supervised learning for image classification. arXiv preprint arXiv:1905.00546 (2019)

  66. 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)

    Google Scholar 

  67. 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)

    Google Scholar 

  68. 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)

    Google Scholar 

  69. Yang, Y., Eriguchi, A., Muzio, A., Tadepalli, P., Lee, S., Hassan, H.: Improving multilingual translation by representation and gradient regularization. arXiv preprint arXiv:2109.04778 (2021)

  70. Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. arXiv preprint arXiv:2001.06782 (2020)

  71. 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)

    Google Scholar 

  72. 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)

    Google Scholar 

  73. 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)

    Google Scholar 

  74. 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

    Chapter  Google Scholar 

  75. 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)

    Article  Google Scholar 

  76. Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vision 127(3), 302–321 (2019)

    Article  Google Scholar 

  77. Zhou, X., Koltun, V., Krähenbühl, P.: Simple multi-dataset detection. arXiv preprint arXiv:2102.13086 (2021)

  78. Zhuang, L., Sun, M., Zhou, T., Gao, H., Darrell, T.: Rethinking the value of network pruning (2018)

    Google Scholar 

  79. 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 Media 6(4), 477–487 (2020). https://doi.org/10.1007/s41095-020-0184-6

    Article  Google Scholar 

Download references

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

Authors

Corresponding author

Correspondence to Yu Qiao .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 193 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

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

  • DOI: https://doi.org/10.1007/978-3-031-19809-0_29

  • 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)

Publish with us

Policies and ethics