Skip to main content
SpringerLink
Log in

Trapped in Texture Bias? A Large Scale Comparison of Deep Instance Segmentation

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13668))

Included in the following conference series:

  • 1658 Accesses

Abstract

Do deep learning models for instance segmentation generalize to novel objects in a systematic way? For classification, such behavior has been questioned. In this study, we aim to understand if certain design decisions such as framework, architecture or pre-training contribute to the semantic understanding of instance segmentation. To answer this question, we consider a special case of robustness and compare pre-trained models on a challenging benchmark for object-centric, out-of-distribution texture. We do not introduce another method in this work. Instead, we take a step back and evaluate a broad range of existing literature. This includes Cascade and Mask R-CNN, Swin Transformer, BMask, YOLACT(++), DETR, BCNet, SOTR and SOLOv2. We find that YOLACT++, SOTR and SOLOv2 are significantly more robust to out-of-distribution texture than other frameworks. In addition, we show that deeper and dynamic architectures improve robustness whereas training schedules, data augmentation and pre-training have only a minor impact. In summary we evaluate 68 models on 61 versions of MS COCO for a total of 4148 evaluations.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
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

Notes

  1. 1.

    Stylized Datasets: https://github.com/bethgelab/stylize-datasets.

  2. 2.

    See supplementary material for the list of code projects and weight sources.

References

  1. Baker, N., Lu, H., Erlikhman, G., Kellman, P.J.: Deep convolutional networks do not classify based on global object shape. PLoS Comput. Biol. 14(12), e1006613 (2018)

    Article  Google Scholar 

  2. Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. CoRR abs/2004.10934 (2020)

    Google Scholar 

  3. Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: YOLACT: real-time instance segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (Oct 2019)

    Google Scholar 

  4. Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: YOLACT++: better real-time instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1108–1121 (2020)

    Article  Google Scholar 

  5. Brendel, W., Bethge, M.: Approximating CNNs with bag-of-local-features models works surprisingly well on ImageNet. In: International Conference on Learning Representations (2019)

    Google Scholar 

  6. Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  7. Cao, A., Johnson, J.: Inverting and understanding object detectors. CoRR abs/2106.13933 (2021)

    Google Scholar 

  8. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision – ECCV 2020, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13

    Chapter  Google Scholar 

  9. Chang, N., Yu, Z., Wang, Y.X., Anandkumar, A., Fidler, S., Alvarez, J.M.: Image-level or object-level? A tale of two resampling strategies for long-tailed detection. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 1463–1472. PMLR (2021)

    Google Scholar 

  10. Chen, X., Fan, H., Girshick, R.B., He, K.: Improved baselines with momentum contrastive learning. CoRR abs/2003.04297 (2020)

    Google Scholar 

  11. Chen, Y.T., Liu, X., Yang, M.H.: Multi-instance object segmentation with occlusion handling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)

    Google Scholar 

  12. Chen, Y., et al.: Scale-aware automatic augmentation for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9563–9572 (2021)

    Google Scholar 

  13. Cheng, T., Wang, X., Huang, L., Liu, W.: Boundary-preserving mask R-CNN. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision – ECCV 2020, vol. 12359, pp. 660–676. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_39

    Chapter  Google Scholar 

  14. Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)

    Google Scholar 

  15. Dosovitskiy, A., et al.: An image is worth 16 \(\times \) 16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)

    Google Scholar 

  16. Fan, Q., Ke, L., Pei, W., Tang, C.K., Tai, Y.W.: Commonality-parsing network across shape and appearance for partially supervised instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision – ECCV 2020, vol. 12353, pp. 379–396. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58598-3_23

    Chapter  Google Scholar 

  17. Geirhos, R., Narayanappa, K., Mitzkus, B., Bethge, M., Wichmann, F.A., Brendel, W.: On the surprising similarities between supervised and self-supervised models (2020)

    Google Scholar 

  18. Geirhos, R., et al.: Partial success in closing the gap between human and machine vision. CoRR abs/2106.07411 (2021)

    Google Scholar 

  19. Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In: International Conference on Learning Representations (2019)

    Google Scholar 

  20. Geirhos, R., Temme, C.R.M., Rauber, J., Schütt, H.H., Bethge, M., Wichmann, F.A.: Generalisation in humans and deep neural networks. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018)

    Google Scholar 

  21. Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 2918–2928 (2021)

    Google Scholar 

  22. Greff, K., van Steenkiste, S., Schmidhuber, J.: On the binding problem in artificial neural networks. CoRR abs/2012.05208 (2020)

    Google Scholar 

  23. Guo, R., Niu, D., Qu, L., Li, Z.: SOTR: segmenting objects with transformers. CoRR abs/2108.06747 (2021)

    Google Scholar 

  24. He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    Google Scholar 

  25. He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (Oct 2017)

    Google Scholar 

  26. He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision – ECCV 2014, vol. 8691, pp. 346–361. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_23

    Chapter  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 (CVPR) (2016)

    Google Scholar 

  28. Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: International Conference on Learning Representations (2019)

    Google Scholar 

  29. Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15262–15271 (2021)

    Google Scholar 

  30. Hsieh, T.I., Robb, E., Chen, H.T., Huang, J.B.: DropLoss for long-tail instance segmentation. In: Proceedings of the Workshop on Artificial Intelligence Safety 2021 (SafeAI 2021) Co-Located with the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021), Virtual, February 8, 2021 (2021)

    Google Scholar 

  31. Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  32. Hu, R., Dollár, P., He, K., Darrell, T., Girshick, R.: Learning to segment every thing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  33. Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)

    Google Scholar 

  34. Huang, Z., Huang, L., Gong, Y., Huang, C., Wang, X.: Mask scoring R-CNN. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)

    Google Scholar 

  35. Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: CCNet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  36. Islam, M.A., et al.: Shape or texture: understanding discriminative features in \(\{\)CNN\(\}\)s. In: International Conference on Learning Representations (2021)

    Google Scholar 

  37. Kamann, C., Rother, C.: Benchmarking the robustness of semantic segmentation models with respect to common corruptions. Int. J. Comput. Vis. 129(2), 462–483 (2021)

    Article  Google Scholar 

  38. Ke, L., Tai, Y.W., Tang, C.K.: Deep occlusion-aware instance segmentation with overlapping BiLayers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4019–4028 (2021)

    Google Scholar 

  39. Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR) (2017)

    Google Scholar 

  40. Kirillov, A., Wu, Y., He, K., Girshick, R.: PointRend: image segmentation as rendering. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    Google Scholar 

  41. Lau, F., Subramani, N., Harrison, S., Kim, A., Branson, E., Liu, R.: Natural adversarial objects. arXiv preprint arXiv:2111.04204 (2021)

  42. Leclerc, G., et al.: 3DB: a framework for debugging computer vision models. CoRR abs/2106.03805 (2021)

    Google Scholar 

  43. Li, Y., et al.: Shape-texture debiased neural network training. In: International Conference on Learning Representations (2021)

    Google Scholar 

  44. Lin, T.Y., Dollar, 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 (CVPR) (2017)

    Google Scholar 

  45. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision – ECCV 2014, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  46. Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  47. Liu, Z., et al.: Swin Transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)

  48. Madan, S., Sasaki, T., Li, T.M., Boix, X., Pfister, H.: Small in-distribution changes in 3D perspective and lighting fool both CNNs and Transformers. CoRR abs/2106.16198 (2021)

    Google Scholar 

  49. Mahmood, K., Mahmood, R., van Dijk, M.: On the robustness of vision transformers to adversarial examples. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7838–7847 (2021)

    Google Scholar 

  50. Michaelis, C., et al.: Benchmarking robustness in object detection: autonomous driving when winter is coming. In: Machine Learning for Autonomous Driving Workshop, NeurIPS 2019, vol. 190707484 (2019)

    Google Scholar 

  51. Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    Google Scholar 

  52. Mummadi, C.K., Subramaniam, R., Hutmacher, R., Vitay, J., Fischer, V., Metzen, J.H.: Does enhanced shape bias improve neural network robustness to common corruptions? In: International Conference on Learning Representations (2021)

    Google Scholar 

  53. Pan, T.Y., et al.: On model calibration for long-tailed object detection and instance segmentation. In: Thirty-Fifth Conference on Neural Information Processing Systems (2021)

    Google Scholar 

  54. Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Dollar, P.: Designing network design spaces. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    Google Scholar 

  55. Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do ImageNet classifiers generalize to ImageNet? In: Proceedings of Machine Learning Research, vol. 97, pp. 5389–5400. PMLR, Long Beach, California, USA (2019)

    Google Scholar 

  56. Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. CoRR abs/1804.02767 (2018)

    Google Scholar 

  57. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates, Inc. (2015)

    Google Scholar 

  58. Shankar, V., Roelofs, R., Mania, H., Fang, A., Recht, B., Schmidt, L.: Evaluating machine accuracy on ImageNet. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 8634–8644. PMLR (Jul 2020)

    Google Scholar 

  59. Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 97, pp. 6105–6114. PMLR (2019)

    Google Scholar 

  60. Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., Isola, P.: What makes for good views for contrastive learning? In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 6827–6839. Curran Associates, Inc. (2020)

    Google Scholar 

  61. Tian, Z., Shen, C., Chen, H.: Conditional convolutions for instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision – ECCV 2020, vol. 12346, pp. 282–298. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_17

    Chapter  Google Scholar 

  62. Tian, Z., Shen, C., Chen, H., He, T.: FCOS: Fully convolutional one-stage object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  63. Tuli, S., Dasgupta, I., Grant, E., Griffiths, T.L.: Are convolutional neural networks or transformers more like human vision? CoRR abs/2105.07197 (2021)

    Google Scholar 

  64. Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Scaled-YOLOv4: scaling cross stage partial network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13029–13038 (2021)

    Google Scholar 

  65. Wang, C.Y., Mark Liao, H.Y., Wu, Y.H., Chen, P.Y., Hsieh, J.W., Yeh, I.H.: CSPNet: a new backbone that can enhance learning capability of CNN. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1571–1580. IEEE, Seattle, WA, USA (2020)

    Google Scholar 

  66. Wang, J., et al.: Seesaw loss for long-tailed instance segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9695–9704 (2021)

    Google Scholar 

  67. Wang, T., et al.: The devil is in classification: a simple framework for long-tail instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision – ECCV 2020, vol. 12359, pp. 728–744. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_43

    Chapter  Google Scholar 

  68. Wang, X., Kong, T., Shen, C., Jiang, Y., Li, L.: SOLO: segmenting objects by locations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision – ECCV 2020, vol. 12363, pp. 649–665. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58523-5_38

    Chapter  Google Scholar 

  69. Wang, X., Zhang, R., Kong, T., Li, L., Shen, C.: SOLOv2: dynamic and fast instance segmentation. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 17721–17732. Curran Associates, Inc. (2020)

    Google Scholar 

  70. Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)

    Article  Google Scholar 

  71. Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  72. Xie, S., Girshick, R., Dollar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

    Google Scholar 

  73. Yuille, A., Liu, C.: Deep Nets: what have they ever done for vision? Technical Report 88, Center for Brains, Minds and Machines. CBMM, MIT CSAIL (2018)

    Google Scholar 

  74. Yung, J., et al.: SI-Score: an image dataset for fine-grained analysis of robustness to object location, rotation and size. CoRR abs/2104.04191 (2021)

    Google Scholar 

  75. Zhu, C., Zhang, X., Li, Y., Qiu, L., Han, K., Han, X.: SharpContour: a contour-based boundary refinement approach for efficient and accurate instance segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4392–4401 (2022)

    Google Scholar 

  76. Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable ConvNets V2: more deformable, better results. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute for Applied AI - Hochschule der Medien, Stuttgart, Germany

    Johannes Theodoridis, Jessica Hofmann & Johannes Maucher

  2. University of Tübingen, Tübingen, Germany

    Johannes Theodoridis & Andreas Schilling

Authors
  1. Johannes Theodoridis
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jessica Hofmann
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Johannes Maucher
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Andreas Schilling
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Johannes Theodoridis .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 9836 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

Theodoridis, J., Hofmann, J., Maucher, J., Schilling, A. (2022). Trapped in Texture Bias? A Large Scale Comparison of Deep Instance Segmentation. 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 13668. Springer, Cham. https://doi.org/10.1007/978-3-031-20074-8_35

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20074-8_35

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20073-1

  • Online ISBN: 978-3-031-20074-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation